Skills/ClawHub/iterate-skill

iterate-skill@3.9.4

CAUTION

Publisher claims: "Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update system with mandatory SHA256 checksum verification. v3.0 adds a dual-mode (the original iterate mode plus a defensive-programming mode via /iterate defensive) that performs normal incremental coding tasks with defensive discipline end-to-end." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher jingzhao-l · joined 15 days agoInstalls 3,279Last detonated 6d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-31 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.4sprocessexited 1: ModuleNotFoundError: No module named 'yaml'
0.4sprocessscript backend runs setup only
0.4sprocessscript backend runs setup only

Static findings

MEDIUM
Python subprocess execution detectediterate_cli/guard.py:27 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectediterate_cli/guard.py:185 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectediterate_cli/guard.py:274 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Destructive file system command detectediterate_cli/doctor.py:653 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsSKILL.md:421 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectediterate_cli/guard.py:246 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsSKILL.md:14 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectediterate_cli/completion.py:551 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectediterate_cli/guard.py:105 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commanditerate_cli/guard.py:378 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsSKILL.md:287 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packageSKILL.md:1206 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:364 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detectediterate_cli/doctor.py:697 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectediterate_cli/signing.py:326 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Destructive file system command detectediterate_cli/doctor.py:245 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or deviceiterate_cli/doctor.py:697 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patterniterate_cli/personalize.py:224 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
npx invocation of non-well-known packageiterate_cli/cli.py:278 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:1201 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detectedscripts/validate.py:263 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectediterate_cli/signing.py:259 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagenpm-installer/bin/cli.js:11 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagenpm-installer/test/mode.test.js:283 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandnpm-installer/test/mode.test.js:420 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagenpm-installer/bin/cli.js:10 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/install.py:2460 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectediterate_cli/signing.py:306 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandnpm-installer/lib/installer.js:734 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagenpm-installer/test/mode.test.js:3 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagenpm-installer/bin/cli.js:12 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Remote installer piped to shelliterate_cli/personalize.py:224 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedscripts/install.py:554 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagenpm-installer/test/security.test.js:2 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandnpm-installer/test/mode.test.js:437 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanditerate_cli/signing.py:244 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectediterate_cli/signing.py:211 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandnpm-installer/lib/installer.js:764 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanditerate_cli/updater.py:899 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/install.py:543 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandnpm-installer/test/mode.test.js:449 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagenpm-installer/lib/installer.js:2 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandnpm-installer/test/mode.test.js:252 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageiterate_cli/personalize.py:145 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandnpm-installer/test/mode.test.js:416 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectediterate_cli/updater.py:906 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagenpm-installer/bin/cli.js:13 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectediterate_cli/personalize.py:148 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commanditerate_cli/updater.py:927 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagenpm-installer/bin/cli.js:9 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Access to sensitive file pathsnpm-installer/test/tarball.test.js:209 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagenpm-installer/lib/installer.js:1485 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Access to sensitive file pathsnpm-installer/test/tarball.test.js:211 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actioniterate_cli/wizard.py:85 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagenpm-installer/test/tarball.test.js:2 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/install.py:1549 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/install.py:1463 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/install.py:1532 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/publish_qoder.py:424 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/publish_qoder.py:203 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/publish_qoder.py:406 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/publish_qoder.py:229 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/install.py:2044 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/install.py:1612 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Not measured yet; benchmarks are collected with each run since November 5, 2026. See the MCP server benchmarks.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  3. Unclaimed publisher≈ +8 on the totalClaim jingzhao-l: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jingzhao-lPropose a patch to the maintainer
iterate-skill@3.9.4 safety verdict: Caution 68/100 — KillerSkills