xy-traffic
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from a local file (atoms.jsonl) or a remote vendor API (api.xyskill.xyz) and incorporates the findings into its responses, creating a surface for indirect prompt injection.\n
- Ingestion points: External data is ingested through the atoms-search.py script from references/atoms.jsonl or https://api.xyskill.xyz.\n
- Boundary markers: The instructions do not define delimiters to isolate the retrieved content or provide warnings to the agent to disregard instructions within that data.\n
- Capability inventory: The skill executes a local Python script to perform searches and generates reports based on the script's output.\n
- Sanitization: There is no explicit sanitization of the retrieved data to filter out potential injection patterns.\n- [EXTERNAL_DOWNLOADS]: The skill uses a script to fetch information from the vendor's diagnostic API at https://api.xyskill.xyz. This is a standard feature used to provide evidence-based strategy recommendations.
Audit Metadata