web-app-security-inspection
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze data from external, potentially untrusted sources like web applications and APIs.
- Ingestion points: The skill ingests data from live web pages, HTTP traffic (XHR/Fetch), API responses (GraphQL/REST), and client-side storage via browser automation and the Chrome DevTools Protocol (CDP).
- Boundary markers: The instructions do not define specific delimiters or "ignore" directives to isolate external content from the agent's core instructions.
- Capability inventory: The agent is empowered to navigate web pages, interact with form elements, intercept network requests, and inspect browser runtime state.
- Sanitization: While the skill advises redacting PII and credentials in the final output, it does not include guidelines for sanitizing or escaping malicious content embedded in the web application's responses during the analysis phase.
Audit Metadata