value-prop-statements
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from project files and user input to generate marketing copy, creating an attack surface for indirect instructions.\n
- Ingestion points: Ingests product context, ICP details, and gap statements from /foundation/brain.md (Sections 1, 2, 3), and processes positioning statements provided by the user.\n
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious embedded commands in the source positioning text or brain content.\n
- Capability inventory: The skill's capabilities are restricted to reading local markdown files (/foundation/brain.md, /context/skill-sessions.md) and appending session logs to /context/skill-sessions.md. It does not have network access or subprocess execution rights.\n
- Sanitization: There is no explicit logic described for sanitizing or escaping external content before it is interpolated into the prompt, though Step 4 (Trace-check) serves as a logical validation layer against unintended output changes.
Audit Metadata