cliffhanger-craft
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWSAFE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to process untrusted user content (story drafts and descriptions) to provide creative advice. While it lacks explicit boundary markers for user input, it possesses no high-risk capabilities such as file system modification, network access, or command execution. Evidence Chain: 1. Ingestion points: User-provided narrative content. 2. Boundary markers: Absent. 3. Capability inventory: No subprocess calls, file-writes, or network operations. 4. Sanitization: Absent.
- [SAFE] (SAFE): No malicious code, obfuscation, or unauthorized data access patterns were detected across any of the analyzed files.
Audit Metadata