folk
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to read and write data to the Folk CRM, including contacts, leads, and activities. This process introduces an attack surface for indirect prompt injection, as data retrieved from external CRM records could potentially contain malicious instructions. The skill does not currently define specific boundary markers or data sanitization procedures for these inputs.
- Ingestion points: CRM resources including contacts, companies, leads, and opportunities accessed through the Apideck API (SKILL.md).
- Capability inventory: CRM resource management (list, create, update) and arbitrary downstream API requests via the Apideck Proxy API (SKILL.md).
- Boundary markers: None identified.
- Sanitization: No explicit sanitization or filtering of retrieved CRM data is described.
- [EXTERNAL_DOWNLOADS]: The skill references the @apideck/unify Node.js library and provides links to official documentation and API specifications hosted on apideck.com and folk.app. These are recognized as legitimate vendor resources associated with the skill author and the integrated service.
Audit Metadata