is-this-photo-real

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use several system tools for media analysis, providing specific command-line strings for execution.
  • Evidence: Use of ffprobe and mediainfo for stream and container inspection, yt-dlp for video retrieval, and exiftool for metadata extraction (reference/tool-catalogue.md).
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because it ingests untrusted media files and processes them with shell-based tools.
  • Ingestion points: External image and video files provided for verification (SKILL.md).
  • Boundary markers: Absent. There are no instructions to delimit or ignore instructions that might be embedded in file metadata or content.
  • Capability inventory: Subprocess execution via ffprobe, mediainfo, yt-dlp, and exiftool (reference/tool-catalogue.md).
  • Sanitization: Absent. The skill does not specify how to handle special characters in filenames or metadata fields during command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 12:21 PM
Security Audit — agent-trust-hub — is-this-photo-real