market-context
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-provided market reports, customer interview notes, and analyst reports to update the /foundation/brain.md file.
- Ingestion points: User input (Args/Prompts) and existing content in /foundation/brain.md.
- Boundary markers: The skill requires explicit user confirmation before writing changes, showing a 'before/after' diff.
- Capability inventory: The skill writes to /foundation/brain.md and appends to /context/skill-sessions.md.
- Sanitization: None explicitly mentioned beyond manual review by the user.
Audit Metadata