Skills/ClawHub/codecast

codecast@4.1.0

CAUTION· static only

Publisher claims: "Stream coding agent sessions (Claude Code, Codex, Gemini CLI, etc.) to a Discord channel in real-time via webhook. Use when invoking coding agents and wantin..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher allanjeng · publishing for 276 daysInstalls 3,009Last detonated 7 h ago

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.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 59/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Discord webhook URL. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This 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

MEDIUM
Process kill commandscripts/dev-relay.sh:245 · Process kill command — agent can terminate processeskill "$RELAY_PID" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/dev-relay.sh:259 · Process kill command — agent can terminate processeskill "$AGENT_PID" 2>/dev/null; sleep 1; kill -9 "$AGENT_PID" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/discord-bridge.py:215 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/discord-bridge.py:19 · Process kill command — agent can terminate processes!kill Kill a session: !kill <PID>Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/test-smoke.sh:37 · File permission modification command — agent changes file ownership/permissionsfail "$(basename "$script") is not executable — run: chmod +x $script"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedscripts/platforms/discord.py:85 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandSKILL.md:74 · Process kill command — agent can terminate processesprocess kill sessionId:<id> # Stop sessionFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/dev-relay.sh:214 · File permission modification command — agent changes file ownership/permissionschmod +x "$CMD_FILE"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandscripts/dev-relay.sh:258 · Process kill command — agent can terminate processesif kill -0 "$AGENT_PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/discord-bridge.py:162 · Process kill command — agent can terminate processesreturn False, f"Failed to kill {pid}: {e}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/dev-relay.sh:241 · Process kill command — agent can terminate processeswhile kill -0 "$RELAY_PID" 2>/dev/null; doFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/discord-bridge.py:279 · Process kill command — agent can terminate processes# --- Command: !kill <PID> ---Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/discord-bridge.py:50 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/discord-bridge.py:283 · Process kill command — agent can terminate processesreply(channel_id, "Usage: `!kill <PID>`")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/codecast-watch.sh:11 · Process kill command — agent can terminate processesif kill -0 "$PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Discord webhook URLscripts/dev-relay.sh:143 · Discord webhook URL — data will be sent to Discord[ -z "$WEBHOOK_URL" ] && { echo "❌ Error: .webhook-url not found in $SCRIPT_DIR" >&2; echo " Create it: echo 'https://discord.com/api/webhooks/ID/TOKEN' > $SCRIPT_DIR/.webhook-url" >&2; exit 1; }Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/platforms/discord.py:23 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, timeout=10, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Fake instruction boundary tagreferences/advanced-modes.md:23 · Fake instruction boundary tag · informational: not an instruction file| `-p <prompt>` | Custom review prompt | Standard code review |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈1,029 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

21 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim allanjeng: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Discord webhook URL≈ +4 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim allanjengPropose a patch to the maintainer