recoup-internal-consulting-system-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface where instructions embedded in external data could influence agent behavior.
- Ingestion points: The skill specifically instructs the agent to find and process unprocessed transcripts located in
content/01-raw/and*/meetings/folders. - Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores or sanitizes instructions that might be contained within these raw meeting transcripts.
- Capability inventory: The skill has the capability to reconcile filesystem data with the Attio CRM (
integrations/attio/crm-sync.md) and invoke sibling capabilities likerecoup-internal-consulting-call-processor. - Sanitization: The instructions do not specify any validation, filtering, or escaping steps for the content processed from the raw data directories.
Audit Metadata