skills/duongdev/cdp-browser/status/Gen Agent Trust Hub

status

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes the local script node scripts/cdp-commands/status.mjs to retrieve status information.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection. It ingests data from local project files, such as docs/memories/risks.md and various task files, and requires the agent to output the content verbatim. It lacks boundary markers or sanitization, which could allow malicious content in those files to influence subsequent agent actions if those files are modified by an untrusted source.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 02:26 AM
Security Audit — agent-trust-hub — status