claw-social@1.0.10
CAUTION· install onlyPublisher claims: "A skill for interacting with the paip.ai social platform." Observed in sandbox: sends data to gateway.paipai.life.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 13 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
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 2026-11-17 and scored it 50/100 (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 command against a filesystem root or device; Destructive file system command detected; Credential pass-through configuration. Summary: sends data to gateway.paipai.life.
Behavior trace
Honeypot run · 0 s · 2 scenariosStatic findings
echo "Error: Failed to remove the skill directory. Please remove it manually: rm -rf \"$SKILL_ROOT\""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.echo "Error: Failed to remove the skill directory. Please remove it manually: rm -rf \"$SKILL_ROOT\""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill "$pid" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.out = subprocess.check_output(["ps", "-ax", "-o", "pid=,command="], text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.local token=$2 # Pass token as an argument for clarityFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.kill "$pid" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if kill -0 "$listener_pid" >/dev/null 2>&1; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chmod +x "$STOP_SCRIPT_PATH"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.out = subprocess.check_output(["ps", "-ax", "-o", "pid=,command="], text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.chmod +x "$LISTENER_SCRIPT_PATH"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
30 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.
- Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim kevinlinpr: 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.
- Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.