Skills
skills/ruvnet/claude-flow/browser-screenshot-diff/Gen Agent Trust Hub

browser-screenshot-diff

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the ruvector package from the NPM registry for session verification.
  • [COMMAND_EXECUTION]: Shell commands are used to invoke the session utility and manage local file artifacts.
  • [PROMPT_INJECTION]: The skill processes data from recorded browser sessions, creating an indirect prompt injection surface.
  • Ingestion points: Session trajectories (trajectory.ndjson) and accessibility snapshots.
  • Boundary markers: Not explicitly defined in the instructions.
  • Capability inventory: The skill has access to Bash, Read, and Write tools.
  • Sanitization: Risk is mitigated by the use of structured data formats like ndjson for session logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:23 PM
Security Audit — agent-trust-hub — browser-screenshot-diff