legal-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted external data sources such as product documentation and UI text, establishing an ingestion surface for indirect prompt injection.
- Ingestion points: Instructions in SKILL.md reference mapping 'externally visible commitments (docs, UI text)' and 'data-handling flows'.
- Boundary markers: No delimiters or instructions to ignore embedded commands are specified in SKILL.md.
- Capability inventory: No executable scripts, network operations, or tool invocations are present in SKILL.md or referenced files.
- Sanitization: No input validation, filtering, or sanitization logic is described in SKILL.md.
- [NO_CODE]: The skill consists exclusively of natural language instructions and YAML metadata without any accompanying scripts, binaries, or automated tasks.
Audit Metadata