release

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes git and gh (GitHub CLI) to manage the repository lifecycle, including branch switching, pulling updates, pushing tags, and triggering GitHub Actions workflows for deployment.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the project repository to guide the release workflow.
  • Ingestion points: The agent is instructed to read pyproject.toml, uv.lock, and existing GitHub Release notes from the repository in SKILL.md.
  • Boundary markers: There are no specific delimiters defined to isolate data from instructions.
  • Capability inventory: The skill possesses the ability to execute shell commands using git and gh tools across all steps in SKILL.md.
  • Sanitization: The instructions require the agent to manually review file contents and confirm version status, which serves as a procedural safeguard.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 02:32 PM