screenwriter
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (LOW): The skill possesses an indirect prompt injection surface because it processes untrusted user-supplied story ideas to generate outputs. Evidence Chain: 1. Ingestion points: Phase 1 story ideas in
SKILL.md. 2. Boundary markers: None present. 3. Capability inventory: Purely text-based output; no subprocess execution, network access, or file-write capabilities are defined. 4. Sanitization: None. While the risk of system compromise is non-existent, the generated output could be manipulated by adversarial input.
Audit Metadata