release

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs standard software development operations, such as version management and Git history analysis, using built-in agent capabilities and official CLI tools (git, gh).
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes untrusted data from commit messages and the changelog.
  • Ingestion points: Reads Git history via git log and parses CHANGELOG.md for versioning logic and release notes.
  • Boundary markers: None present; the instructions do not specify delimiters or instructions to ignore embedded commands.
  • Capability inventory: Uses Bash for git/gh commands and Write/Edit for file updates in the local repository.
  • Sanitization: No explicit sanitization or filtering of commit messages or changelog content is defined.
  • Note: This surface is inherent to the functionality of release automation tools and is considered acceptable within this context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 10:07 AM
Security Audit — agent-trust-hub — release