changelog-generator

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists of documentation and usage examples for generating changelogs. No security vulnerabilities or malicious patterns were identified.
  • [NO_CODE]: The skill does not provide any scripts, configuration files, or external dependencies. It relies entirely on the agent's natural language processing capabilities.
  • [PROMPT_INJECTION]: The skill is designed to process git commit messages, which are considered untrusted external data. This creates a surface for indirect prompt injection.
  • Ingestion points: Git commit messages retrieved from the repository history via SKILL.md.
  • Boundary markers: The instructions do not specify delimiters or markers to separate commit content from instructions.
  • Capability inventory: Reading git history and writing markdown text.
  • Sanitization: No specific sanitization or filtering logic is provided for the commit message content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 06:38 AM