Skills
Navigate
skills/c0x12c/ai-toolkit/browser-qa/Gen Agent Trust Hub

browser-qa

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from web pages during its QA routines.\n
  • Ingestion points: The skill captures web content and console logs using page.goto and page.on('console') as shown in playwright-snippets.md.\n
  • Boundary markers: The skill lacks explicit markers to distinguish between untrusted browser data and operational instructions.\n
  • Capability inventory: The skill is configured with access to Bash, Write, Edit, and Read tools in the SKILL.md frontmatter.\n
  • Sanitization: There is no evidence of sanitization or filtering of data retrieved from the target web pages.\n- [DYNAMIC_EXECUTION]: The skill generates and executes browser automation scripts using provided templates.\n
  • Evidence: The file playwright-snippets.md contains TypeScript code snippets for Playwright that the agent is expected to execute to perform QA tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 03:02 PM