business-kickoff-workshop
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted user-provided content such as transcripts and notes.
- Ingestion points: The skill ingests external data in Phase 1 (customer context) and Phase 2 (call transcripts).
- Boundary markers: Absent. The instructions do not specify delimiters to separate untrusted transcript data from the system's operational instructions.
- Capability inventory: The skill includes the capability to write data to local markdown files (e.g.,
bmc-[customername]-[date].md). - Sanitization: Absent. There is no validation or filtering mentioned for the ingested data, relying on the agent's ability to synthesize the text appropriately.
Audit Metadata