youtube-scriptwriting
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- Prompt Injection (SAFE): No instructions to override agent behavior or bypass safety guidelines were detected.
- No Code (SAFE): The skill is purely markdown-based and does not contain any scripts, binaries, or shell commands.
- Indirect Prompt Injection (INFO): The skill identifies a surface for indirect prompt injection as it processes external user content such as transcripts and research notes. However, it lacks any exploitable capabilities to perform actions beyond text transformation. Ingestion points: Processes user-provided source material (transcripts, research). Boundary markers: Not specified in the instructions. Capability inventory: Text transformation and formatting only; no tool use or execution. Sanitization: None specified.
Audit Metadata