changelog-generator
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from git histories and local files. 1. Ingestion points: Git commit messages and project-specific configuration files such as CHANGELOG_STYLE.md. 2. Boundary markers: Absent; no explicit delimiters or warnings are defined to separate untrusted commit data from agent instructions. 3. Capability inventory: The skill relies on reading git history and writing results to the local filesystem (e.g., CHANGELOG.md). 4. Sanitization: Absent; the skill does not instruct the agent to sanitize or escape commit message content before processing.
- [NO_CODE]: The skill consists exclusively of instructional text in the SKILL.md file and does not include any accompanying scripts, executables, or automated configuration files.
Audit Metadata