requirements-analyst
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill workflow is centered on processing untrusted external data which creates a vulnerability to indirect prompt injection.
- Ingestion points: Workflow step 1 and Interaction Protocol specify processing 'PRD, tickets, user feedback, and stakeholder requests' from file
SKILL.md. - Boundary markers: Absent. There are no instructions for the agent to use delimiters or to ignore instructions embedded within the ingested data.
- Capability inventory: The skill generates structured text and 'handoff artifacts' for downstream agents such as
development-implementerandsolution-architect. - Sanitization: Absent. No validation or filtering logic is defined for external content.
- No Executable Code (SAFE): Analysis of
SKILL.mdandagents/openai.yamlconfirms the absence of scripts, binaries, or package dependencies.
Audit Metadata