pre-mortem
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes untrusted external data and has the capability to write to the local file system.
- Ingestion points: The instructions direct the agent to read user-provided PRD or product plan files and to use web search for market research (Step 1).
- Boundary markers: The skill does not define explicit delimiters or include instructions for the agent to ignore potentially malicious embedded instructions within the ingested documents or search results.
- Capability inventory: The skill is instructed to save its analysis as a markdown document on the local file system (Step 7).
- Sanitization: There are no requirements for sanitizing, validating, or escaping the external content before it is processed or written to disk.
Audit Metadata