Skills
Navigate
skills/jarmen423/skills/core-agent-browser/Gen Agent Trust Hub

core-agent-browser

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interfaces with the agent-browser CLI to perform web automation tasks including navigation, element interaction (click, fill), and information retrieval (get text/value).
  • [PROMPT_INJECTION]: As the skill ingests and processes content from external websites via the snapshot command, it is susceptible to indirect prompt injection attacks where malicious instructions on a webpage could influence the agent's behavior.
  • Ingestion points: agent-browser snapshot and agent-browser get text outputs in SKILL.md.
  • Boundary markers: No delimiters or 'ignore' instructions are present in the documentation to mitigate processing untrusted HTML content.
  • Capability inventory: Subprocess execution via agent-browser for interaction and navigation; file system writes via agent-browser screenshot (SKILL.md).
  • Sanitization: No specific sanitization, escaping, or validation of external webpage content is described in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 05:48 PM
Security Audit — agent-trust-hub — core-agent-browser