to-tickets

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and process potentially untrusted data from external sources.
  • Ingestion points: The skill fetches and reads the body and comments of existing GitHub issues or external spec files (Step 1).
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between the skill's logic and the content of the processed issues.
  • Capability inventory: The skill can create, comment on, and edit GitHub issues using the gh CLI tool (Step 5).
  • Sanitization: The risk is mitigated by a mandatory human-in-the-loop checkpoint ('Step 4: Quiz the user') where the agent must present the proposed breakdown for manual approval before publishing.
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to perform repository management tasks. These operations are standard developer workflow commands (create, list, view, edit, comment, close) and are executed within the local repository environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 03:47 PM
Security Audit — agent-trust-hub — to-tickets