linkfox-kalodata-tiktok-livestream

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data such as TikTok livestream titles and creator handles retrieved via API, which constitutes a potential surface for indirect prompt injection. This behavior is expected for a data retrieval tool and is well-scoped.
  • Ingestion points: Livestream data returned from the Kalodata API endpoints in scripts/kalodata_livestream_search.py and scripts/kalodata_livestream_detail.py.
  • Boundary markers: No explicit delimiters or instructions are present to differentiate external data from agent commands.
  • Capability inventory: The skill can write data to local project files and perform authenticated POST requests to the vendor's API gateway.
  • Sanitization: External content is currently presented without explicit filtering or sanitization.
  • [EXTERNAL_DOWNLOADS]: The scripts/onboarding.py script references standard Python packages (requests, qrcode, pillow) as optional dependencies for its login and QR code generation features. These are well-known libraries and do not represent a security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 09:09 AM
Security Audit — agent-trust-hub — linkfox-kalodata-tiktok-livestream