shipped-issues

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard development tools (git, gh, sf) to perform its maintenance tasks. Commands are structured to retrieve data from the repository and internal systems without exposing the environment to arbitrary execution.
  • [DATA_EXPOSURE]: It retrieves GitHub issue bodies and changelog content to identify candidates for closing. This data is handled locally within temporary files (/tmp) and is necessary for the skill's primary function.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from GitHub issue bodies using a regex pattern (W-\d{6,9}) to identify work items. While this involves processing external data, the risk of injection is mitigated by the narrow extraction logic and the requirement for explicit user confirmation in Step 7 before any issue is closed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 08:53 PM
Security Audit — agent-trust-hub — shipped-issues