recoup-internal-consulting-testimonial-capture
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest project results and client data to draft testimonials and emails, creating a potential attack surface for indirect prompt injection.
- Ingestion points: Processes project data, verified results, and workspace configuration files such as
AGENTS.mdandDESIGN.md. - Boundary markers: The instructions lack specific boundary markers or delimiters to help the agent distinguish between data to be processed and instructions to be followed.
- Capability inventory: The skill requires read access to workspace files and write access to the
proof/testimonials/directory. - Sanitization: No explicit sanitization, validation, or filtering of the ingested data is defined in the workflow.
Audit Metadata