maven-search
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of Maven metadata and artifacts from official, well-known services including
search.maven.organdrepo1.maven.org. These sources are standard for Java development and are handled neutrally. - [COMMAND_EXECUTION]: Instructions describe the use of standard HTTP GET requests to interact with REST APIs and repository paths to fetch Project Object Model (POM) files and metadata.
- [DATA_EXPOSURE]: Analysis confirms no hardcoded credentials, API keys, or access to sensitive local file paths (such as SSH keys or environment configurations).
- [PROMPT_INJECTION]: No evidence of malicious override markers, jailbreak attempts, or instructions to ignore safety protocols was found in the skill body or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to ingest and parse external XML data (POM files) from Maven Central. While this constitutes an untrusted data ingestion surface, the skill targets a well-known repository and does not grant the agent high-privilege capabilities that could be abused via malicious metadata in a library.
Audit Metadata