taapi

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs HTTP GET and POST requests to https://api.taapi.io using the system's proxied client. This is the intended behavior for fetching technical indicators from the TaAPI well-known service.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes data from an external source.\n
  • Ingestion points: Data is retrieved from the TaAPI API in tools/indicators.py and tools/support_resistance.py.\n
  • Boundary markers: Indicator data is output in JSON or concise string formats; specific delimiters to isolate data from agent instructions are not explicitly used.\n
  • Capability inventory: Includes network access via proxied_get and proxied_post across multiple scripts.\n
  • Sanitization: The skill validates JSON structure. While no natural language instruction filtering is present, the numeric and technical nature of the data source poses a negligible risk.\n- [SAFE]: The skill does not contain hardcoded credentials, obfuscation, or persistence mechanisms. It correctly manages authentication using environment variables and lacks any unauthorized command execution patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 10:07 PM