inspect-in-devtools
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external DevTools comment threads.
- Ingestion points: Data enters the agent's context through the get_devtools_comments tool in SKILL.md, which retrieves user-generated or system-generated text from the browser's DevTools UI.
- Boundary markers: Absent; the instructions do not specify the use of delimiters or sanitization routines for the content of these comments.
- Capability inventory: The skill in SKILL.md has significant capabilities, including executing scripts via evaluate_script and modifying files in the workspace to apply fixes based on the comments received.
- Sanitization: Absent; there is no mention of escaping or validating the content of the comment threads before they are used to inform code changes or script execution.
Audit Metadata