msw-search
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill communicates with an internal IP (10.10.200.51) and a development domain (nxdev.kr) to retrieve search results and resource metadata. These operations are consistent with the skill's documented purpose. No exfiltration of sensitive information or unauthorized access to local files was detected.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from search results. While this represents an indirect prompt injection surface, the risk is assessed as low due to the technical and structured nature of the retrieved content (API documentation and asset metadata).
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The provided Python script (msw_resource_api.py) relies exclusively on Python standard libraries (urllib, json, argparse). It does not download external packages or execute untrusted remote code.
Audit Metadata