ecommerce-tiktok-creator-search-api

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external creator data from the Kalodata API, which represents an ingestion surface for untrusted content.\n
  • Ingestion points: Data is retrieved from the provider via the call_api function in scripts/kalodata_creator_search.py.\n
  • Boundary markers: The prompt instructions do not specify explicit delimiters for the ingested data, but include rules for summarizing results.\n
  • Capability inventory: The skill performs authenticated network requests and writes JSON artifacts to the local filesystem for caching and session history.\n
  • Sanitization: The skill implements recursive redaction for sensitive fields like tokens and passwords as defined in the display rules in SKILL.md.\n- [DATA_EXPOSURE]: The skill adheres to security best practices by managing credentials through environment variables rather than hardcoding or passing them as CLI arguments.\n
  • Evidence: scripts/kalodata_creator_search.py retrieves the NEXSCOPE_API_KEY from the environment and includes logic to prevent secrets from being persisted in output artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 05:40 AM
Security Audit — agent-trust-hub — ecommerce-tiktok-creator-search-api