xy-course
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes a bundled Python script (atoms-search.py) to retrieve pedagogical reference data from api.xyskill.xyz. This connection is used strictly for fetching instructional content for the courses.
- [COMMAND_EXECUTION]: The agent is instructed to run a local helper script to search the internal knowledge base. The script relies on standard Python libraries and operates within the skill's directory.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize user-provided materials or existing project files to generate curricula. To mitigate risks associated with untrusted data, the instructions contain strict prohibitions against accessing sensitive files such as .env, SSH keys, or financial documents.
- [SAFE]: The skill exhibits a strong security posture by explicitly defining file access boundaries and limiting its data ingestion to relevant project documentation.
Audit Metadata