Skills/ClawHub/taskhold

taskhold@1.0.0

CAUTION

Publisher claims: "Work from the task list the user shares with their coding agents through the Taskhold MCP server (https://taskhold.com/api/mcp, Bearer key from a Taskhold setup URL). Use at the start of a coding session and when the user says "work on the next task", "what's next", "what's on my list", "pick up my next todo", "check my task list", "file this as a task", "add a TODO for later", "put this on the backlog", "remind me to fix this later", "mark that done", "leave a note on the task", "what did the agent do", "turn these TODO comments into tasks", "what's in progress", or "I'm blocked on this". Also use when you need the human to decide something (block the task with a question). For the session's built-in todo checklist or a repo TODO.md the user points at, use those directly. For production errors and crash reports, use the user's error tracker." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher jakemarsh · joined 0 days agoInstalls 122Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-10-27 and scored it 66/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials. 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

HIGH
Prompting user to enter sensitive credentialsSKILL.md:48 · Prompting user to enter sensitive credentials — social engineeringFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03

No other findings across 106 lines in 2 files.

What would make this Verified

14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim jakemarsh: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Prompting user to enter sensitive credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jakemarsh