breakdown-epic-arch
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes external data from a Product Requirements Document (PRD).
- Ingestion points: Untrusted data from the PRD is interpolated into the context template within SKILL.md.
- Boundary markers: The prompt template lacks explicit delimiters or specific instructions (e.g., 'ignore embedded commands') to distinguish the PRD data from the agent's core instructions.
- Capability inventory: The skill has the capability to write the resulting specification to the local filesystem at /docs/ways-of-work/plan/{epic-name}/arch.md.
- Sanitization: There is no sanitization or validation of the PRD content before it is processed by the agent.
Audit Metadata