instagram-video-downloader

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the vendor's API endpoint at https://redfox.hk/story/api/parseWork/videoDownload/instagram to retrieve video metadata and download links. This is the primary intended function of the skill.
  • [COMMAND_EXECUTION]: The skill is designed to be executed via a Python script (scripts/downloader.py) which processes user-provided Instagram URLs. The script uses standard libraries and validates input before making API calls.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it retrieves and displays the description of Instagram posts. An attacker could place malicious instructions in a post's caption that would then be processed by the agent.
  • Ingestion points: scripts/downloader.py retrieves the desc field from the API response and prints it to the console.
  • Boundary markers: No explicit delimiters are used when displaying retrieved content.
  • Capability inventory: The script performs network requests and maintains a configuration file in the user's home directory (~/.qoder/apis/redfox.json).
  • Sanitization: No sanitization or filtering is applied to the retrieved post descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 07:24 AM
Security Audit — agent-trust-hub — instagram-video-downloader