media-archiver

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads image assets from user-provided external URLs to populate a local directory at ./web/images.
  • [PROMPT_INJECTION]: The skill is instructed to ingest untrusted content from the web and copy text verbatim, which creates a surface for indirect prompt injection attacks.
  • Ingestion points: Target URLs provided by the user and accessed via a browser tool.
  • Boundary markers: None; the skill is explicitly told to keep all text content verbatim with no omissions.
  • Capability inventory: File system write access (restricted to the ./web directory) and browser navigation.
  • Sanitization: No validation or sanitization of the external HTML or text content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 05:05 PM
Security Audit — agent-trust-hub — media-archiver