cta-interest-based
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional, providing a bank of approved phrases and a scoring methodology for marketing copy. It does not include any scripts, dependencies, or external resources.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data in the form of user-provided email drafts or output from other copywriting skills. Ingestion points: Outreach copy and CTA drafts (SKILL.md). Boundary markers: Absent. Capability inventory: None. Sanitization: Absent. While it lacks explicit safety boundaries for external data, the risk is negligible because the skill does not possess any exploitable capabilities such as file system access, command execution, or network connectivity.
Audit Metadata