skills/unlearndev/skills/checklist/Gen Agent Trust Hub

checklist

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a legitimate utility for tracking project progress through local markdown files.
  • [DATA_EXFILTRATION]: No evidence of credential harvesting, access to sensitive system paths, or external data transmission was found.
  • [COMMAND_EXECUTION]: Shell command usage is restricted to directory management and file listing within the project scope.
  • [PROMPT_INJECTION]: The instructions for the agent to update the checklist are functional and do not attempt to override core safety protocols.
  • [PROMPT_INJECTION]: The skill ingests conversation content from context to create files without explicit sanitization or boundary markers. While this creates a surface for processing untrusted instructions, the capability is limited to writing markdown files, which is consistent with the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 04:08 PM