skills/dcjanus/prompts/pwdebug/Gen Agent Trust Hub

pwdebug

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts via scripts/pwdebug.py to facilitate browser control and debugging operations.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external websites via browser navigation and JavaScript evaluation. This constitutes a surface for indirect prompt injection. Ingestion points: URL navigation and DOM interactions; Boundary markers: None specified in the documentation; Capability inventory: Arbitrary JavaScript execution and network navigation; Sanitization: Not explicitly implemented for external web content.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes uv for dependency management, which may retrieve required libraries from standard package registries at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 07:22 AM