engagement-setup
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, including client documentation and stakeholder interview notes, to generate project outputs such as agendas and charters.
- Ingestion points: Both SKILL.md and references/discovery-methods.md involve processing client-provided evidence and interview reports.
- Boundary markers: The instructions lack specific delimiters or isolation markers to separate external data from the agent's core instructions during processing.
- Capability inventory: The skill relies on generative text capabilities to produce kickoffs, charters, and synthesis reports, but it does not invoke high-privilege tools or network operations.
- Sanitization: The skill provides mitigation guidance by instructing the agent to sanitize shared materials and distinguish between observed facts and paraphrased accounts.
Audit Metadata