founder-ops
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather information from external websites (supplier pricing, wage statistics, and government permit portals) and incorporate it into local project files. Because the instructions do not define delimiters or provide guidance on sanitizing untrusted external content, the skill is susceptible to indirect prompt injection. Malicious instructions placed on researched websites could potentially influence the agent's logic or the content of the generated files.
- Ingestion points: External web research for suppliers (Step 2), wages (Step 3), tools (Step 5), and permits (Step 6); local files
founder/idea.md,founder/offer.md, andfounder/numbers.json. - Boundary markers: None present in the instructions.
- Capability inventory: The skill has file-write access to
founder/ops.mdandfounder/numbers.json. - Sanitization: No validation or escaping of external data is specified.
Audit Metadata