Skills/ClawHub/agent-roundtable

agent-roundtable@1.2.4

CAUTION· static only

Publisher claims: "Multi-agent roundtable discussion — topic-driven multi-round debate with convergence detection and conclusion generation" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher parsifalc · publishing for 172 daysInstalls 1,053Last detonated 33 min ago
What would fix thisWatchDispute verdict

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 2026-11-14 and scored it 60/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Hidden zero-width characters detected; Hidden zero-width characters detected. 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
Python subprocess execution detectedSKILL.md:563 · Python subprocess execution detected…that `_hermes_send_fn` is implemented and passed to the core. The send_fn uses `subprocess.run(["python3", script, profile, chat_id, message])` to call `feishu-send.py`. 15. *…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Hidden zero-width characters detectedsrc/roundtable/demo.py:273 · Hidden zero-width characters detected — may conceal contenticon = {"全栈工程师": "👩‍💻", "架构师": "👨‍💻", "产品经理": "👩‍💼"}.get(role, "👤")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Hidden zero-width characters detectedsrc/roundtable/demo.py:259 · Hidden zero-width characters detected — may conceal contenticon = {"全栈工程师": "👩‍💻", "架构师": "👨‍💻", "产品经理": "👩‍💼"}.get(p.get("role", ""), "👤")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Hidden zero-width characters detectedsrc/roundtable/adapters/base.py:14 · Hidden zero-width characters detected — may conceal contentreturn {"name": "Alice", "role": "engineer", "avatar": "👩‍💻"}Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedsrc/roundtable/web_publisher.py:406 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/roundtable/adapters/hermes.py:42 · 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
Python subprocess execution detectedSKILL.md:334 · Python subprocess execution detected…tarting a discussion with `web=True` should automatically open the browser via `subprocess.run(["open", web_url])` in the Hermes adapter's `_handle_init`. This is an **adapter…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Hidden zero-width characters detectedsrc/roundtable/adapters/simple.py:16 · Hidden zero-width characters detected — may conceal contentavatar="👩‍💻",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedSKILL.md:336 · Python subprocess execution detected… after the discussion concludes (or manually). The `_handle_init` code has the `subprocess.run(["open", web_url])` call, but it may not fire reliably in all execution paths. *…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/roundtable/adapters/hermes.py:136 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, timeout=5)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/roundtable/web_publisher.py:323 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Hidden zero-width characters detectedsrc/roundtable/demo.py:17 · Hidden zero-width characters detected — may conceal content"avatar": "👩‍💻",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedsrc/skills/SKILL.md:563 · Python subprocess execution detected…that `_hermes_send_fn` is implemented and passed to the core. The send_fn uses `subprocess.run(["python3", script, profile, chat_id, message])` to call `feishu-send.py`. 15. *…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/skills/SKILL.md:336 · Python subprocess execution detected… after the discussion concludes (or manually). The `_handle_init` code has the `subprocess.run(["open", web_url])` call, but it may not fire reliably in all execution paths. *…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/skills/SKILL.md:334 · Python subprocess execution detected…tarting a discussion with `web=True` should automatically open the browser via `subprocess.run(["open", web_url])` in the Hermes adapter's `_handle_init`. This is an **adapter…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈17,851 tok
2 files · 115 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

20 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim parsifalc: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim parsifalcPropose a patch to the maintainer