mcp-sanitizer@1.4.4
CAUTION· install onlyPublisher claims: "Comprehensive security sanitization library for Model Context Protocol (MCP) servers with trusted security libraries" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What changed since 1.4.3
vet-skills diff mcp-sanitizer 1.4.3 1.4.4In the sandbox, this version reached for nothing 1.4.3 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-16 and scored it 74/100 (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 · 0 s · 1 scenarios · 0 deviationsStatic findings
'rm -rf', 'del /s', 'format', 'mkfs',Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./\.env/i // Environment filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'.npmrc', '.netrc', '.env', '.git-credentials',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.return await validators.sql.sanitize(input, options);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.return await validators.sql.validate(input, options);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.'sudo rm', 'sudo del'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.// user's home directory (e.g. ~/.ssh/id_rsa) pass with blocked=false.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'.env', '.example', '.template'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.blockedDirectories: ['/etc/passwd', '/etc/shadow']Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// user's home directory (e.g. ~/.ssh/id_rsa) pass with blocked=false.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// Directory or file names that hold credentials; `.env.*` is matched separately.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* substrings, so a sensitive first segment (`.env`, `.ssh/id_rsa`) is caught.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* console.log('Sanitized input:', result.sanitized);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.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
6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim starman69: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- 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.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- 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.