requirements-elicitation
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted product documents (PRDs, feature specs, user stories, roadmaps, and one-pagers) provided by users. A malicious actor could embed hidden instructions within these documents to influence the agent's analysis or output.
- Ingestion points: Workflow Phase 1 in
SKILL.mdinstructs the agent to "Read the entire document" and analyze its content. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" directives for the external documents being analyzed.
- Capability inventory: The skill produces text-based Markdown reports. Based on the provided files, it does not invoke external tools, perform network operations, or execute shell commands.
- Sanitization: There is no mention of sanitizing or filtering input text before processing.
Audit Metadata