business-experiment-coach
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and analyzing untrusted business data and project materials provided by the user, which could potentially contain malicious instructions.
- Ingestion points: As described in SKILL.md, the agent is instructed to read user-pointed records, project materials, and evidence links to inform its coaching and diagnosis.
- Boundary markers: The skill mitigates accidental obedience by instructing the agent to strictly separate user reports, verifiable facts, and inferences within its internal logic.
- Capability inventory: The skill instructs the agent to summarize findings and write project state information to a local file named business-state.md.
- Sanitization: The instructions do not specify technical sanitization or filtering methods for the external content before processing.
Audit Metadata