cold-email-subject-lines
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate or critique email subjects, creating a surface for potential instruction injection.
- Ingestion points: Variable inputs for
audience,evp, andintent, as well as user-provided subject lines for critique inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to treat user data as untrusted content.
- Capability inventory: The skill is restricted to
ReadandGreptool usage. - Sanitization: No validation or sanitization of external user input is defined.
Audit Metadata