technical-articles
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely composed of natural language instructions and writing examples. It does not contain any executable scripts, binaries, or command-line operations.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing user-provided content such as voice transcripts and chat logs to generate articles. While this provides a surface for indirect prompt injection, the skill lacks the capabilities (tools, network access, or file-writing permissions) required to execute an attack, rendering the surface benign.\n
- Ingestion points: User-supplied transcripts and brainstorm logs mentioned in the 'When the User Gave You the Voice, Use It' section.\n
- Boundary markers: None present for external content.\n
- Capability inventory: None; the skill does not use any tools or scripts.\n
- Sanitization: None present.
Audit Metadata