skills/huangwb8/skills/auto-draw-plot/Gen Agent Trust Hub

auto-draw-plot

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified during the analysis of the skill's instructions and scripts.
  • [COMMAND_EXECUTION]: The skill executes internal Python scripts to manage multi-round image generation tasks. It utilizes shlex.quote to sanitize arguments and file paths before execution, effectively mitigating command injection risks.
  • [CREDENTIALS_UNSAFE]: The skill retrieves API keys from standard local configuration files (such as ~/.codex/auth.json). It implements robust redaction logic to ensure these secrets are masked in debug outputs and metadata files, preventing accidental exposure in logs.
  • [EXTERNAL_DOWNLOADS]: The skill establishes network connections to author-controlled and well-known service endpoints (api.benszresearch.com and generativelanguage.googleapis.com) for image generation. These interactions are transparently documented and consistent with the skill's primary function.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 03:21 AM
Security Audit — agent-trust-hub — auto-draw-plot