course-direction-advisor
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no malicious patterns, command execution, or sensitive data access. It is focused on analytical tasks using provided documentation.
- [PROMPT_INJECTION]: Evaluated for indirect prompt injection potential. 1. Ingestion points: User-provided source documents and transcripts as defined in input-contract.md. 2. Boundary markers: Implementation of evidence indexing (SRC-001) and trace maps. 3. Capability inventory: Web-based market research and structured report generation. 4. Sanitization: Use of strict gating rules that forbid fabricating methods or cases not present in the material.
- [DATA_EXFILTRATION]: Evaluated network operations. The B-market-scan mode involves research of public market signals (competitors, demand) which is a functional requirement and does not involve access to or exfiltration of sensitive local data.
Audit Metadata