create-changelog
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from repository history, such as commit messages and pull request descriptions, which could contain malicious instructions. * Ingestion points: Repository metadata, commit history, and pull request descriptions are read to gather evidence (SKILL.md Step 1). * Boundary markers: The skill instructs the agent to follow a specific structure from 'references/example-changelog.md' and keep entries concise. * Capability inventory: The agent reads local files and repository history, then writes the 'CHANGELOG.md' file to the repository root. * Sanitization: Step 5 (Verify) explicitly requires checking that 'no unsupported claims... or generated commit dumps remain,' which acts as a verification layer against potentially malicious content embedded in the repository history.
- [EXTERNAL_DOWNLOADS]: The documentation provides an installation command that references the author's own repository on GitHub. * Evidence: 'npx skills add SirDarcanos/agentskills --skill create-changelog' in README.md.
Audit Metadata