recoup-internal-consulting-expansion-spotter
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data (client notes, delivery documents, and value reviews) which could potentially contain malicious instructions intended to influence the agent's behavior during the expansion analysis.
- Ingestion points: Step 1 in SKILL.md instructs the agent to scan client notes and value reviews.
- Boundary markers: None present.
- Capability inventory: The skill has file-writing capabilities to the client-specific project directory (Step 3).
- Sanitization: No explicit sanitization or validation of the ingested client data is described.
Audit Metadata