Contribute Skill

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gh CLI to check authentication status and programmatically create issues on GitHub. This involves executing shell commands with parameters derived from the agent's session.- [PROMPT_INJECTION]: There is an indirect prompt injection surface as the skill ingests untrusted user input and incorporates it into a shell command.
  • Ingestion points: Free-text responses from the user regarding knowledge sources, skill descriptions, and contributor notes.
  • Boundary markers: The skill template does not define clear delimiters or use 'ignore instructions' warnings for the interpolated content.
  • Capability inventory: The skill is capable of executing gh issue create (network/write) and writing to the local cache directory ~/.cache/awesome-neuro-skills/.
  • Sanitization: The instructions lack specific requirements for sanitizing or escaping shell-sensitive characters within the user-provided data before command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 09:51 PM