changelog-generator
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the command
git log --oneline --no-mergesto retrieve commit history. This is a standard and safe use of git for the purpose of identifying recent project changes and does not involve any dangerous parameters or piping to shells. - [PROMPT_INJECTION]: The skill processes git commit messages, which are external data. While this presents a surface for indirect prompt injection if a commit message contains malicious instructions, the risk is considered low because the skill's capabilities are limited to text categorization and formatting without any dangerous downstream actions.
- Ingestion points: Commit messages retrieved via
git log(SKILL.md). - Boundary markers: Absent.
- Capability inventory: Markdown formatting and text categorization. No file system writes, network requests, or code execution capabilities are present.
- Sanitization: Absent.
Audit Metadata