skills/daxaur/openpaw/c-browser/Gen Agent Trust Hub

c-browser

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted content from the web through browser snapshots and scraping, creating a surface for indirect prompt injection. Ingestion points: Web page content accessed via snapshots and scraping (SKILL.md). Boundary markers: None specified in the instructions. Capability inventory: Full browser navigation and interaction (click, fill, type, press). Sanitization: No specific sanitization or filtering of external web content is mentioned.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes agent-browser and playwright-cli for its browser automation capabilities. These are well-known tools provided by Vercel and Microsoft, which are trusted organizations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:44 AM
Security Audit — agent-trust-hub — c-browser