ito-ui-verify
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configuration instructs the execution of
npx chrome-devtools-mcp@latest, which fetches the tool from the official NPM registry. This is a standard procedure using a well-known package registry. - [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) to view repository metadata and create new issues for reporting identified UI failures. It also writes structured report data to the local file system in thedocs/ito-temp/ui-verify/directory. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by ingesting and acting upon content retrieved from web browser sessions.
- Ingestion points: External data is ingested through DOM snapshots, console log messages, and network request details captured via the
chrome-devtools-mcptools. - Boundary markers: The instructions include a dedicated 'Security Boundary' section that explicitly directs the agent to treat browser-retrieved content as untrusted data rather than authoritative instructions.
- Capability inventory: The agent possesses the capability to write files to the local disk and interact with GitHub repositories to create issues.
- Sanitization: The skill does not define specific technical sanitization or validation logic for the ingested web data; it relies on adherence to the provided safety instructions.
Audit Metadata