Skills
Navigate
skills/blockmatic/basilic-skills/debug-browser/Gen Agent Trust Hub

debug-browser

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to use browser tools to navigate and interact with websites, creating a surface where untrusted content from the web could influence agent behavior.
  • Ingestion points: The agent uses browser_navigate and browser_snapshot to ingest data from external URLs as described in SKILL.md.
  • Boundary markers: No delimiters or specific instructions to disregard instructions within the browser content are present.
  • Capability inventory: The agent uses browser_navigate, browser_click, and browser_snapshot tools.
  • Sanitization: No explicit sanitization or filtering of the content retrieved via browser tools is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 10:29 PM
Security Audit — agent-trust-hub — debug-browser