video-frame-extractor

Fail

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: HIGHCREDENTIALS_UNSAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill contains a hardcoded API key for the Coze platform in both SKILL.md and scripts/coze_bot_client.py. The key cztei_qHZQ0A5OSJjsmfZWmVb8bqu2BTbtB240YGbDYLhZpsIr8jER4aL4Aevyii8rnKfNs is provided as a default value and in configuration examples, exposing it to unauthorized use.
  • [DATA_EXFILTRATION]: The scripts scripts/coze_bot_client.py and scripts/visual_analyzer.py read local image files and transmit them to external endpoints, including https://api.coze.cn/v3/chat and other user-configurable vision API providers like OpenAI.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection where malicious instructions embedded within video frames could influence the behavior of the vision model or downstream agents.
  • Ingestion points: Visual content from video frames processed by AI models in scripts/visual_analyzer.py and scripts/coze_bot_client.py.
  • Boundary markers: Absent; the prompt templates provided in references/analysis-guide.md do not include instructions for the model to ignore text or instructions found within the images.
  • Capability inventory: The skill can write to the local file system (scripts/video_frame_extractor.py) and perform network requests (scripts/visual_analyzer.py).
  • Sanitization: No sanitization or validation is performed on the data returned by the vision APIs before it is saved to structured JSON files.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 27, 2026, 01:20 AM
Security Audit — agent-trust-hub — video-frame-extractor