image-seo

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from user-provided URLs, which introduces a surface for indirect prompt injection.
  • Ingestion points: Data enters the context via the user-supplied website or page URL specified in the argument-hint.
  • Boundary markers: The instructions do not define clear delimiters or "ignore" instructions for the content fetched from the external URL.
  • Capability inventory: The skill performs network operations to fetch HTML and image metadata, and subsequently analyzes this data.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the external source.
  • [DYNAMIC_EXECUTION]: The skill uses a directive to load a workflow from a local relative path (../../seo/image-seo/SKILL.md). This effectively delegates execution to another component within the local environment and is a standard architectural pattern for organizing skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 03:14 PM
Security Audit — agent-trust-hub — image-seo