seo-images

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of system CLI tools including exiftool, cwebp, convert (ImageMagick), and ffmpeg to read/write image metadata and perform format conversions.
  • [PRIVILEGE_ESCALATION]: The documentation instructs the user to execute sudo apt install commands to install the necessary image processing libraries on their system.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external URLs and image files, which presents a surface for indirect prompt injection.
  • Ingestion points: External web pages via the [url] argument and existing image file metadata during optimization routines.
  • Boundary markers: None identified in the skill instructions to separate untrusted data from processing logic.
  • Capability inventory: Subprocess calls to exiftool, cwebp, and ImageMagick are used to manipulate files based on extracted metadata.
  • Sanitization: No explicit sanitization or validation of the extracted alt text or metadata is documented before being passed to shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 09:06 PM