make-changes
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute repository-specific commands like
pnpm changes:previewand linting tools to verify changelog entries and maintain code quality. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests data from PR diffs and commit ranges to generate release notes.
- Ingestion points: PR diffs and commit ranges (SKILL.md)
- Boundary markers: None identified
- Capability inventory: Execution of
pnpmscripts and linting tools (SKILL.md) - Sanitization: None identified
- Context: This behavior is a core requirement for the skill's functionality and is typical for developer tools.
Audit Metadata