Agency
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data during the client intake process, such as extracting scope from emails, audio transcripts, or documents.
- Ingestion points: The intake workflow in
onboarding.mdandSKILL.mdinstructs the agent to process external communications and documents to generate structured briefs and client profiles. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when handling or interpolating external content.
- Capability inventory: The skill's operations are confined to local file management within
~/Clawic/data/agency/and it does not utilize network operations or arbitrary shell execution. - Sanitization: There are no explicit requirements for sanitizing or validating external intake content before it is processed by the agent.
Audit Metadata