gemini-image
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied image descriptions and interpolates them directly into browser automation commands via
camofox type. - Ingestion points: The skill takes image prompts from the user in sections 2 and 4 of
SKILL.md. - Boundary markers: There are no explicit delimiters or warnings to the agent to disregard instructions that might be embedded within the user-provided prompt.
- Capability inventory: The
camofoxtool has significant capabilities including browser navigation, clicking, typing, and executing arbitrary JavaScript viacamofox eval(mentioned in the error recovery section). - Sanitization: The skill does not implement any validation or sanitization of the user input before passing it to the CLI tool for interaction with the web interface.
Audit Metadata