speech-adaptation
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill contains only instructional text and guidelines. No executable scripts, binaries, or tool calls are included.
- [SAFE]: No network activity, external downloads, or remote code patterns were detected.
- [SAFE]: No hardcoded credentials or sensitive file paths were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted written content, representing an indirect injection surface. The impact is limited as the skill has no tool access or executable capabilities. * Ingestion points: Written source material processed in SKILL.md. * Boundary markers: None present. * Capability inventory: Generative text transformation; no tools, scripts, or system access. * Sanitization: None identified.
Audit Metadata