Skills/ClawHub/claw-social

claw-social@1.0.10

CAUTION· install only

Publisher claims: "A skill for interacting with the paip.ai social platform." Observed in sandbox: sends data to gateway.paipai.life.

Registry ClawHubPublisher kevinlinpr · publishing for 246 daysInstalls 1,402Last detonated 23 min ago

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 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1:
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1: FATAL: TOKEN or PAIPAI_TOKEN environment variable must be set.
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexec /app/apps/web/node_modules/.bin/ps
0.2sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/ps
0.2sprocessexec /app/node_modules/.bin/ps
0.2sprocessexec /pnpm/ps
0.2sprocessexec /usr/local/sbin/ps
0.2sprocessexec /usr/local/bin/ps
0.2sprocessexec /usr/sbin/ps
0.2sprocessexec /usr/bin/ps
0.2sprocessexec /sbin/ps
0.2sprocessexec /bin/ps
0.2sprocessexec /usr/bin/rm
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2snetworkCONNECT tcp://gateway.paipai.life:443 · not in the allow-list, refused
0.2sprocessexec /usr/bin/base64
0.2sprocessexec /usr/bin/curl
0.2sprocessexited 56:
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexec /usr/bin/dirname
0.3sprocessexec /usr/bin/chmod
0.3sprocessexec /app/apps/web/node_modules/.bin/ps
0.3sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/ps
0.3sprocessexec /app/node_modules/.bin/ps
0.3sprocessexec /pnpm/ps
0.3sprocessexec /usr/local/sbin/ps
0.3sprocessexec /usr/local/bin/ps
0.3sprocessexec /usr/sbin/ps
0.3sprocessexec /usr/bin/ps
0.3sprocessexec /sbin/ps
0.3sprocessexec /bin/ps
0.3sprocessexec /usr/bin/rm
0.3sprocess8 of 13 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.3sprocessscript backend runs setup only
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

CRITICAL
Destructive command against a filesystem root or devicescripts/uninstall.sh:53 · Destructive command against a filesystem root or deviceecho "Error: Failed to remove the skill directory. Please remove it manually: rm -rf \"$SKILL_ROOT\""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedscripts/uninstall.sh:53 · Destructive file system command detectedecho "Error: Failed to remove the skill directory. Please remove it manually: rm -rf \"$SKILL_ROOT\""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/stop_websocket_listener.sh:42 · Process kill command — agent can terminate processeskill "$pid" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/stop_websocket_listener.sh:13 · Python subprocess execution detectedout = 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.
AST05
HIGH
Credential pass-through configurationscripts/social.sh:18 · Credential pass-through configuration — agent relays sensitive credentialslocal token=$2 # Pass token as an argument for clarityFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Process kill commandscripts/start_websocket_listener.sh:68 · Process kill command — agent can terminate processeskill "$pid" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/start_websocket_listener.sh:88 · Process kill command — agent can terminate processesif kill -0 "$listener_pid" >/dev/null 2>&1; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/uninstall.sh:16 · File permission modification command — agent changes file ownership/permissionschmod +x "$STOP_SCRIPT_PATH"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedscripts/start_websocket_listener.sh:23 · Python subprocess execution detectedout = 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.
AST05
MEDIUM
File permission modification commandscripts/login_and_listen.sh:110 · File permission modification command — agent changes file ownership/permissionschmod +x "$LISTENER_SCRIPT_PATH"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈4,568 tok
1 file · 16 in bundle

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%
  1. 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.
  2. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. 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.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. 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.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim kevinlinprPropose a patch to the maintainer