Release Notes Generator
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a pure text-processing prompt. It does not utilize any platform tools, perform network requests, or access sensitive files.
- [PROMPT_INJECTION]: The skill ingests untrusted data from git history and pull requests, creating a surface for indirect prompt injection. However, the instructions mandate that the agent rewrite and categorize the input into specific sections (e.g., 'New Features', 'Bug Fixes'), which inherently mitigates the risk of the agent executing commands found within the source text.
Audit Metadata