axiom-validate-screenshots

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the sips (Scriptable Image Processing System) command, a standard macOS utility, to extract image dimensions for validation. This is a common and safe practice for the described functionality.
  • [REMOTE_CODE_EXECUTION]: No remote code execution or untrusted downloads were detected. The skill operates on local files provided by the user.
  • [DATA_EXFILTRATION]: The skill does not perform any network operations or external data transmissions. Analysis is performed locally using the agent's vision capabilities.
  • [PROMPT_INJECTION]: The instructions contain clear guidelines for the AI to follow a specific workflow without attempts to bypass safety filters or override system instructions.
  • [EXTERNAL_DOWNLOADS]: No external dependencies, packages, or scripts are downloaded; all logic is contained within the markdown instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 08:49 PM
Security Audit — agent-trust-hub — axiom-validate-screenshots