xy-question-spec
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions guide the agent to execute a local Python utility script (
scripts/atoms-search.py) to search for relevant knowledge units (atoms) based on user input.\n- [EXTERNAL_DOWNLOADS]: Theatoms-search.pyscript makes network requests tohttps://api.xyskill.xyzto retrieve or synchronize knowledge data.\n- [DATA_EXFILTRATION]: The search utility accesses the user's home directory to read~/.xy/config.jsonand transmits search queries to a remote server. This behavior is consistent with the skill's search and configuration functionality.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files and API responses, creating a surface for indirect prompt injection.\n - Ingestion points: Knowledge data is retrieved from the local
references/atoms.jsonlfile and theapi.xyskill.xyzAPI.\n - Boundary markers: The instructions do not define explicit delimiters for the retrieved data.\n
- Capability inventory: The skill can execute Python scripts.\n
- Sanitization: The script does not perform specific sanitization of the retrieved knowledge content before it is processed by the agent.
Audit Metadata