vfx-research
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the web via Brave Search and Context7, which could contain instructions designed to influence the agent's behavior.
- Ingestion points: External search results from Brave Search and documentation snippets from Context7 as described in SKILL.md.
- Boundary markers: The instructions lack explicit delimitation or specific instructions to isolate retrieved web content from the agent's core instructions.
- Capability inventory: The skill utilizes web search capabilities and references a local script (
brave_image_search.py) to fetch and display content. - Sanitization: There are no instructions for the agent to sanitize or validate the content of the search results before processing them.
Audit Metadata