agentshield@2.0.2
CAUTION· install onlyPublisher claims: "AI Agent Detection & Response — real-time security monitoring with Sigma rules and LLM-powered triage" Observed in sandbox: sends data to release-assets.githubusercontent.com.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 1 of 1 bundled script run with no arguments, 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
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 55/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Auto-update or dynamic fetch configuration; Access to sensitive file paths. Summary: sends data to release-assets.githubusercontent.com.
Behavior trace
Honeypot run · 3 s · 3 scenariosStatic findings
- '/etc/shadow'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- Hot reload is enabled by default (`rules.hot_reload: true`)Fix: Pin versions and sources; vendor anything fetched at install time.selection: {tool: file_operation, path|contains: ['/etc/passwd', '/etc/shadow', '.ssh/']}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if kill -0 "$e2e_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill "$e2e_pid" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.hot_reload: trueFix: Pin versions and sources; vendor anything fetched at install time.hot_reload: trueFix: Pin versions and sources; vendor anything fetched at install time.- '/etc/passwd'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.chmod +x "$INSTALL_DIR/bin/agentshield"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
25 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
- Unclaimed publisher≈ +8 on the totalClaim markbriers: 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.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.