image

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides shell command examples for image optimization using standard utilities such as cwebp, mogrify, and jpegoptim. These are used appropriately for the skill's stated purpose of optimizing visual assets.
  • [EXTERNAL_DOWNLOADS]: Includes an example using curl to fetch the source code of a website for auditing image tags. This is a common and legitimate practice for image performance and SEO analysis.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection attack surface. Ingestion points include reading local context from .agents/product-marketing-context.md and fetching data from external URLs via curl. While boundary markers and sanitization are absent, the skill does not exhibit any malicious behavior or attempts to bypass agent security controls.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 11:09 PM
Security Audit — agent-trust-hub — image