Skills/npm/continuous-improvement

continuous-improvement@3.27.0

CAUTION· install only

Publisher claims: "Guard and memory plugin for Claude Code. As a Claude Code plugin it wires a hook that denies known destructive shell commands in every permission mode; opt-in hooks that deny pushes to protected branches and edits to the files that wire the guardrails, an" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher naimkatiman · publishing for 231 daysInstalls 354Last detonated 22 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 70 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 3.26.0

vet-skills diff continuous-improvement 3.26.0 3.27.0

In the sandbox, this version reached for nothing 3.26.0 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 73/100 (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; Destructive command against a filesystem root or device; Destructive file system command detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 2: usage: get-deployed-sha.sh [--show-command] <provider>
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/git
0.1sprocessexited 1:
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: input required: pass the recommendation text as the positional arg
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessbundled script run in the sandbox with no arguments
0.5sprocessexec /usr/bin/git
0.5sprocessexec /usr/bin/sha256sum
0.5sprocessexec /usr/bin/cut
0.5sprocessexec /usr/bin/basename
0.5sprocess8 of 70 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.5sprocessscript backend runs setup only
0.5sprocessscript backend runs setup only
0.5sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionlib/cli-anything.mjs:30 · File type combined with upload action — agent may exfiltrate local data filesthis.log(`✅ CLI generated: ${outputPath}`);Fix: 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 packagelib/shell-intent.mjs:502 · npx invocation of non-well-known package — may execute untrusted code/** Programs that run the program named after their own options: npx tsc, bunx vitest. */Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedlib/destructive-bash.mjs:644 · Destructive file system command detected// cmd.exe's `del /s` and `erase /s` delete the matching files in everyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or devicelib/destructive-bash.mjs:31 · Destructive command against a filesystem root or device* flag: `bash -c "rm -rf /"` carries a real command and still gates.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagebin/lint-transcript.mjs:64 · npx invocation of non-well-known package — may execute untrusted code* (npm test, npx tsc, node --test, python -m pytest, cargo clippy,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/install.mjs:10 · npx invocation of non-well-known package — may execute untrusted code* npx continuous-improvement install --uninstall # remove everythingFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionbin/harvest-friction.mjs:257 · File type combined with upload action — agent may exfiltrate local data filesconsole.log("WARNING: tool_complete rows found but lack output_summary fields.");Fix: 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 packagebin/backfill.mjs:34 · npx invocation of non-well-known package — may execute untrusted codenpx continuous-improvement backfill Tag rows in placeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/install.mjs:7 · npx invocation of non-well-known package — may execute untrusted code* npx continuous-improvement install --mode expert # + MCP server + session hooksFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detectedlib/destructive-bash.mjs:31 · Destructive file system command detected* flag: `bash -c "rm -rf /"` carries a real command and still gates.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionbin/lint-transcript.mjs:648 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`${state.rowsWithoutInput} rows carry a tool name and no tool input (${THIN_ROWS_NOTE}).`);Fix: 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 packagebin/install.mjs:8 · npx invocation of non-well-known package — may execute untrusted code* npx continuous-improvement install --pack react # load starter instinct packFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionbin/unified-cli.mjs:64 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` Output: ${result.outputPath}`);Fix: 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 packagelib/version-check.mjs:58 · npx invocation of non-well-known package — may execute untrusted code"or npm → npx continuous-improvement install. Silence: CLAUDE_CI_UPDATE_CHECK=off");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionbin/unified-cli.mjs:75 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(" Output format: executable JavaScript");Fix: 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 packagelib/install-targets.mjs:86 · npx invocation of non-well-known package — may execute untrusted code"# Written by `npx continuous-improvement install --target aider`.",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detectedlib/destructive-bash.mjs:62 · Destructive file system command detected"del /q /f",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionlib/cli-anything.mjs:394 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`📁 Output: ${result.outputPath}`);Fix: 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 packagebin/backfill.mjs:35 · npx invocation of non-well-known package — may execute untrusted codenpx continuous-improvement backfill --dry-run Report counts, write nothingFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagelib/install-targets.mjs:17 · npx invocation of non-well-known package — may execute untrusted codeexport const MANAGED_BEGIN = "<!-- continuous-improvement:begin (managed block — reinstall via `npx continuous-improvement install --target <name>`; edits inside are overwritten) -->";Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detectedlib/destructive-bash.mjs:61 · Destructive file system command detected"del /f /q",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionbin/harvest-friction.mjs:250 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(" the Node observer is not on PATH — never tool_complete with output_summary,");Fix: 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 packagelib/plugin-metadata.mjs:77 · npx invocation of non-well-known package — may execute untrusted code…arm/ pinned to upstream SHA addb5cd. Activation note: assets reference unpinned npx @claude-flow/cli@latest — supply-chain risk inert until installed.", source: "./third-party/ruf…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackage.json:4 · npx invocation of non-well-known package — may execute untrusted code…l calls; up to 10 recorded lessons loaded at session start; and an MCP server. `npx continuous-improvement install` wires only the tool-call log (with --mode expert, also the session-sta…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/install.mjs:9 · npx invocation of non-well-known package — may execute untrusted code* npx continuous-improvement install --target gemini,codex # skill into other agents' rules filesFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionbin/generate-plugin-manifests.mjs:208 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Generated ${outputPath}`);Fix: 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 packagebin/install.mjs:6 · npx invocation of non-well-known package — may execute untrusted code* npx continuous-improvement install # beginner mode (default)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionbin/harvest-friction.mjs:258 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(" The classifier needs the rich-schema output_summary to detect failures.");Fix: 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 packagescripts/resolve-verify-ladder.mjs:19 · npx invocation of non-well-known package — may execute untrusted code// typecheck: npx tsc --noEmit (manifest)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesscripts/README.md:28 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file- `bin/` — generated CLI entrypoints (`.mjs` from `src/bin/*.mts`). Do not hand-edit; see [`CLAUDE.md`](../CLAUDE.md) → "Build pipeline".Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈3,457 tok
1 file · 80 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

7 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. Unclaimed publisher≈ +8 on the totalClaim naimkatiman: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. npx invocation of non-well-known package≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim naimkatimanPropose a patch to the maintainer