subject-line-psychologist
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of markdown instructions and personas for text generation tasks. No executable code, scripts, or system commands are present in the file.
- [SAFE]: The instructions incorporate ethical guardrails and failure mode analysis to ensure truthfulness and maintain reader trust, which are safety-positive features.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content for rewriting, establishing an ingestion surface for untrusted data. 1. Ingestion points: User requests for subject line rewriting in SKILL.md. 2. Boundary markers: None specified to separate user data from instructions. 3. Capability inventory: No capabilities for file system access, network communication, or shell execution are utilized. 4. Sanitization: No input filtering or validation is described. Due to the lack of dangerous capabilities, this surface is considered safe.
Audit Metadata