aidlc-requirements
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources to generate project requirements and personas. This creates a surface for indirect prompt injection where malicious instructions embedded in external data could influence the agent.
- Ingestion points: External resources (Figma, API specs), existing requirements files, and web search results are ingested during the generation phase in
actions/generate.md. - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the processed external data.
- Capability inventory: The skill has capabilities to read/write files and perform web searches, which could be leveraged if an injection occurs.
- Sanitization: There is no evidence of sanitization or validation of the content fetched from external URLs or web searches before it is incorporated into the prompt context.
Audit Metadata