recoup-internal-consulting-faq-builder
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown-based process instructions for Recoup staff. It contains no Python scripts, Node.js modules, shell commands, or other executable logic.
- [SAFE]: The instructions focus on organizational tasks such as writing canonical answers to local knowledge base paths and linking related insights. No suspicious network activities, credential harvesting, or obfuscation techniques were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow to process external inputs (consulting requests and answers). While this presents a theoretical surface for indirect prompt injection, the risk is mitigated by the complete absence of executable capabilities or tools that could be exploited by malicious data.
- Ingestion points: Consulting requests and staff answers (SKILL.md).
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: No code, tools, or network access capabilities identified.
- Sanitization: No explicit sanitization of input text described.
Audit Metadata