migrate-orders-to-canonical-schema
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to search codebase files using the Grep tool, which creates an ingestion point for untrusted source code and a potential surface for indirect prompt injection. * Ingestion points: Repository source code files searched via the Grep tool during the Phase 3 audit. * Boundary markers: Absent; no instructions are provided to delimit or ignore potentially malicious instructions found within the audited files. * Capability inventory: Read, Grep, and Bash tools are authorized for use by the agent. * Sanitization: Absent; the workflow does not include steps to validate or filter data returned from the codebase search.
Audit Metadata