release-manager

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted git commit messages to automate changelog generation and versioning, creating a surface for indirect prompt injection where malicious instructions in a commit could influence the agent's behavior. \n
  • Ingestion points: Git commit messages and repository history retrieved via git logs as described in README.md and SKILL.md. \n
  • Boundary markers: The instructions do not define specific delimiters or "ignore" markers to isolate the untrusted commit content from the agent's logic. \n
  • Capability inventory: Writing to the file system (CHANGELOG.md, package manifest files), executing shell commands (git, npm, twine), and performing network operations (pushing to repositories and package registries). \n
  • Sanitization: There is no evidence of sanitization or validation performed on the commit message content before it is processed or written to files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — release-manager