conversion-signal-qa
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data which serves as a potential attack surface for indirect prompt injection.
- Ingestion points: Data from scraped pages, reviews, comments, and emails specified in SKILL.md and references/skill-contract.md.
- Boundary markers: Explicit instructions to treat external data as untrusted input and to disregard embedded instructions are present in the core skill instructions.
- Capability inventory: The skill references optional integration with various marketing platforms (Ads, ESPs, CRMs) via references/connectors.md.
- Sanitization: The instructions mandate that agents must not follow instructions found within evidence, effectively serving as a policy-based sanitization layer.
Audit Metadata