interrogate
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run
git diffcommands to retrieve code changes for analysis. This is a standard and expected operation for a code review tool. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from source code diffs and PR metadata, which presents an attack surface for indirect prompt injection.
- Ingestion points: Untrusted data is ingested from
git diffoutput and PR/commit messages as defined inSKILL.md. - Boundary markers: The skill employs isolation by providing sub-agents with self-contained briefs, preventing them from accessing the full parent context.
- Capability inventory: The skill utilizes shell execution for git commands and the
delegate_tasktool for sub-agent management. - Sanitization: No explicit sanitization or escaping of the diff content is performed before passing it to sub-agents.
Audit Metadata