feasibility-assessor
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its design, which involves processing untrusted external inputs.
- Ingestion points: In
SKILL.md, Phase 1 explicitly instructs the agent to ingest and classify external data, including "Idea pitch", "Feature spec", "Repo/codebase", and "Business plan". - Boundary markers: The instructions do not define boundary markers (e.g., XML tags or delimiters) or provide specific "ignore embedded instructions" directives to prevent the agent from being influenced by malicious content within these inputs.
- Capability inventory: The agent has the capability to perform complex reasoning, scoring, and report generation across multiple scripts, and it is instructed to use
WebSearch(as noted inreferences/financial-viability.md) to aggregate industry data. - Sanitization: There is no mention of sanitizing or validating the ingested content before it is incorporated into the agent's analysis context.
Audit Metadata