release-notes-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run standard Git commands such as git log and git diff to gather release information. These are read-only operations used for repository introspection.
- [INDIRECT_PROMPT_INJECTION]: The skill processes commit messages and file changes which are external inputs that could contain instructions designed to influence the agent's output. 1. Ingestion points: Git logs and diff statistics gathered via shell commands in SKILL.md. 2. Boundary markers: Absent; there are no explicit delimiters or instructions to treat commit data as untrusted. 3. Capability inventory: Shell command execution (git) and text generation for release documentation. 4. Sanitization: No sanitization or validation is applied to the commit messages before they are processed by the agent.
Audit Metadata