maven-code-search
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests code and metadata from third-party Maven artifacts located in the user's local repository.
- Ingestion points: The
extract_source_code,extract_jar_resource, andextract_method_infotools read content directly from external JAR files and source packages into the agent's context (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or provide warnings to the agent about treating the analyzed content as untrusted data.
- Capability inventory: The skill provides read-only access to the Maven repository (~/.m2) via the
maven-decoderMCP server. It does not include tools for writing to the filesystem or initiating network requests. - Sanitization: There is no evidence of sanitization, filtering, or escaping of the content retrieved from the Maven artifacts before it is processed by the agent.
Audit Metadata