vr-avatar-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill integrates tools for fetching external content (SDK documentation, research papers) and possesses capabilities to write files and execute commands. This creates a potential surface for indirect prompt injection if the processed external data contains malicious instructions.
- Ingestion points: Uses WebFetch and mcp__firecrawl__firecrawl_search to retrieve data from external URLs.
- Boundary markers: No explicit instruction for the agent to use delimiters or ignore instructions within external data is present.
- Capability inventory: Access to Write, Edit, and Bash tools provides significant capabilities to modify the system or execute commands.
- Sanitization: Lacks instructions for sanitizing or validating external content before processing.
Audit Metadata