maestro-milestone-release

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute shell commands for git operations, including git commit, git tag, and git push. These actions are necessary for the skill's stated purpose of managing software releases.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8) due to its data ingestion patterns.
  • Ingestion points: The skill reads data from git log and local milestone/phase summaries to generate CHANGELOG.md entries.
  • Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" markers to isolate this external content from the agent's control logic.
  • Capability inventory: The skill has access to Bash (shell execution), Write, and Edit (file system modification).
  • Sanitization: The risk is mitigated by a mandatory confirmation gate using request_user_input, which requires a user to review the release summary (version, milestone name, and changelog count) before any git write or push operations occur.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 06:13 AM
Security Audit — agent-trust-hub — maestro-milestone-release