explain-change
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains purely instructional content for an AI agent to explain software changes. It does not include any scripts, executable code, or requests for sensitive permissions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data such as code diffs and pull request descriptions, which is a common attack surface for indirect prompt injection.
- Ingestion points: Processes diffs, branches, commit ranges, pull requests, and repository documentation (SKILL.md).
- Boundary markers: The instructions explicitly define boundaries, stating the agent should "Stay read-only for explanation-only work" and that "Safety review belongs to an available reviewer; do not present an explanation as merge approval."
- Capability inventory: The skill does not define any scripts, file-system write operations, or network communication capabilities.
- Sanitization: While no technical sanitization is described, the agent is instructed to focus on explaining implementation rather than performing actions, which mitigates the risk of an injection triggering harmful behavior.
Audit Metadata