experimentation-engineer
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides architectural and process guidelines for feature experimentation, including specific operational modes and traceability requirements. No malicious patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill acknowledges the risk of untrusted data and defines security hygiene measures.
- Ingestion points: External data and web content via BrowserOS (SKILL.md).
- Boundary markers: Not explicitly defined in instructions.
- Capability inventory: General references to tool allowlists and terminal execution proxies.
- Sanitization: The framework mandates redacting secrets and PII before sharing context with subagents.
Audit Metadata