outreach
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted research data and prospect information (e.g., research briefs, company info) in Phase 1 to generate outreach messages.
- Ingestion points: Phase 1 (Input Collection) in
SKILL.mddefines several inputs including research briefs and specific hooks. - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the input data.
- Capability inventory: The skill is restricted to text generation and does not utilize any tools for network access, file system modification, or command execution.
- Sanitization: The instructions do not define any sanitization or escaping techniques for the external data before interpolation into the message drafting phase.
Audit Metadata