avatar-spokesperson-production
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill contains only documentation and instructional text; no executable code or scripts are included.
- [SAFE]: The skill focuses on ethical production workflows and legal compliance. No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-related documents. Evidence Chain: (1) Ingestion points: Documents such as client briefs and contracts (SKILL.md). (2) Boundary markers: Present; instructions explicitly separate facts from requirements and heuristics. (3) Capability inventory: None; the skill is purely instructional with no file-write, network, or execution tools. (4) Sanitization: Absent; the workflow relies on human review rather than technical sanitization. Given the lack of tool access, this surface is considered safe.
Audit Metadata