recoup-internal-consulting-case-study-builder
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from client delivery documents which may contain hidden instructions.
- Ingestion points: Data is gathered from the clients/{client}/04-delivery/ directory (SKILL.md).
- Boundary markers: No delimiters or protective instructions are used to separate the external data from the agent's core instructions.
- Capability inventory: The skill can write files to proof/case-studies/ and invoke design-related sibling capabilities.
- Sanitization: There is no process to sanitize or validate the content of the delivery documents to prevent indirect prompt injection attacks.
Audit Metadata