xy-ai-workflow

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill facilitates network requests to an external API (api.xyskill.xyz) via a bundled Python script to fetch knowledge entries. This activity is restricted to retrieving non-sensitive methodology data based on user-provided keywords and does not target system credentials or private files.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user descriptions of their workflows to generate search queries. Although this constitutes a data ingestion surface, the risk is minimal as the ingested content is used solely for information retrieval and the skill does not possess high-privilege execution tools.
  • [COMMAND_EXECUTION]: The skill executes a local script (atoms-search.py) to manage its knowledge retrieval logic. This is a controlled execution of its own code and does not involve running untrusted external payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:22 AM
Security Audit — agent-trust-hub — xy-ai-workflow