scout
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to assist in tool selection and workflow planning, which it performs using standard platform capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data from multiple sources to inform its recommendations. This is a characteristic of its design as a meta-agent. 1. Ingestion points: Conversation context, file system tools (Read, Glob, Grep), and external web tools (WebFetch, WebSearch). 2. Boundary markers: None present in the instructions. 3. Capability inventory: File and directory discovery, web searching, and recommending tool/subagent invocations. 4. Sanitization: No input validation or sanitization is specified.
Audit Metadata