ecommerce-tiktok-video-analytics

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from an external TikTok analytics source, creating a potential surface for instructions embedded in the external content to influence agent behavior.
  • Ingestion points: The scripts scripts/video_detail.py and scripts/video_rank.py retrieve and return JSON data from the Kalodata API proxy.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be contained within the video titles, descriptions, or creator handles retrieved from the API.
  • Capability inventory: The skill is capable of performing network operations (urllib.request.urlopen) and writing to the local filesystem (open(..., 'w')).
  • Sanitization: The Python scripts do not implement filtering or sanitization of the API response data before it is presented to the agent context.
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute Python scripts with user-supplied JSON parameters as command-line arguments.
  • Evidence: python scripts/video_detail.py '<JSON parameters>' and python scripts/video_rank.py '<JSON parameters>' as documented in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 05:40 AM
Security Audit — agent-trust-hub — ecommerce-tiktok-video-analytics