launch-strategy
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external launch data and web content.\n
- Ingestion points: Release framing details and web content ingested via BrowserOS, as mentioned in the 'Security & Multi-Agent Hygiene' section.\n
- Boundary markers: None explicitly defined in the skill instructions.\n
- Capability inventory: Command execution via the 'ExecutionProxy Interface' (e.g.,
rtk npm test) and file writing via the 'MemoryStore Interface' to thedocs/departments/directory.\n - Sanitization: The skill includes mandatory protocols to treat external data as hostile and to redact secrets/PII before sharing context.\n- [SAFE]: The 'GLOBAL PROTOCOLS' and 'Iron Law of Execution' defined in the skill are operational constraints designed to enforce testing and architectural standards rather than attempts to bypass security controls.
Audit Metadata