skills/calicastle/seedhub-cli/seedhub/Gen Agent Trust Hub

seedhub

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The script initiates network connections to seedhub.cc and pan.quark.cn. These are third-party domains required for the scraper's primary function but are not on the pre-approved whitelist.
  • INDIRECT_PROMPT_INJECTION (LOW): The skill processes untrusted data from the web, which represents a surface for indirect prompt injection attacks against an AI agent. 1. Ingestion points: The seedhub.py script fetches HTML content from seedhub.cc using the cloudscraper library. 2. Boundary markers: Absent. The extracted data is returned to the agent without specific boundary markers or instructions to ignore embedded commands. 3. Capability inventory: The script is limited to network GET requests and console output; it does not possess file-writing, system-command execution, or code evaluation capabilities. 4. Sanitization: The clean_desc function performs basic cleaning of HTML entities and removes specific keywords, but does not provide robust protection against malicious instructions embedded in the movie descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 12:58 AM