Skills/npm/satori

satori@6.5.2

CAUTION

Publisher claims: "Claude Code skill & open-source wisdom companion (v6.5.5, Apache 2.0) for CLI, IDE, and web chat. One lens per turn, local SQLite vault, 350-case benchmark (98.0% code non-activation). Install: npx skills add MetcalfSolutions/Satori. Built to be outgrown." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher metcalfsolutions · joined 7 days agoInstalls 1,171Last detonated 7d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-27 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; Prompt injection; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentscripts/satori_memory.py:850 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedscripts/build_release.py:391 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandscripts/install-hooks.sh:4 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/cli.js:4 · 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/validate_skill.py:18 · 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/run_evals.py:1356 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
CRITICAL
Prompt injectionreferences/toolkit-somatic.md:27 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedscripts/satori_memory.py:81 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/generate_benchmark_350.py:279 · 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 pathsscripts/run_evals.py:271 · 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 packagescripts/validate_skill.py:425 · 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 commandscripts/generate_benchmark_350.py:271 · 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/run_evals.py:1328 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
CRITICAL
Prompt injectionREADME.md:418 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsscripts/run_evals.py:267 · 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 detectedscripts/validate_skill.py:429 · 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/cli.js:28 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06

What would make this Verified

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim metcalfsolutions: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. 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.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim metcalfsolutions