trustmcp@0.2.1
BLOCKED· static onlyPublisher claims: "Security scanner for MCP (Model Context Protocol) servers: static (SAST), dynamic (live), and authentication-posture analysis, with an A-F score and SARIF output for the GitHub Security tab." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Before you give it your token
- It will ask for
OPENAI_API_KEY- Where it talks to
- no vendor host named in the codeAlso oasis-open.org, githubusercontent.com, owasp.org — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- nothing has run yet
- What we could not test
- everything: the server has not run yet
Do not connect it. The honeypot or a critical finding blocked this version; the evidence is below.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-20 and scored it 45/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: Access to sensitive file paths; Hidden zero-width characters detected; OS command execution function call detected. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
"remediation": "Move the key to an environment variable loaded from a .env file excluded from version control.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."[" # trustmcp: ignore[static.hidden-unicode]Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."Use the subprocess module with an argument list and shell=False.", "os.popen(...)",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."remediation": "Move the key to an environment variable (e.g. os.getenv('OPENAI_API_KEY')) loaded from a .env file excluded from version control.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."--" # trustmcp: ignore[static.hidden-unicode]Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.# .json/.yaml/.toml/.env files, which produced false positives: aFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Use the subprocess module with an argument list and shell=False.", "os.system(...)",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.".git", "__pycache__", "node_modules", "venv", ".venv", "env", ".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
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
35 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim v0idw4lker: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Bidirectional text override characters detected≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.