changelog-generator
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted commit messages and local style guidelines to generate changelogs. While this behavior is fundamental to the skill's purpose, it creates an inherent surface for indirect prompt injection.
- Ingestion points: Reads git commit history and the CHANGELOG_STYLE.md file.
- Boundary markers: The instructions do not specify delimiters to separate untrusted commit data from agent instructions.
- Capability inventory: The skill requires permissions to read repository history, execute git commands, and write the resulting changelog to the local file system.
- Sanitization: Commit data is processed as-is without specific sanitization steps.
Audit Metadata