maven-search

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to download and parse external XML files, specifically POM files and maven-metadata.xml from Maven Central Repository. While these are legitimate sources, parsing third-party content into the agent's context creates a surface for indirect prompt injection if an attacker-controlled package is processed.
  • Ingestion points: https://repo1.maven.org/maven2/ (via analyze-dependencies.md and get-version-info.md).
  • Boundary markers: None explicitly defined in the instructions for the parsing process.
  • Capability inventory: The skill allows the agent to perform network GET requests and parse structured data (XML/JSON).
  • Sanitization: No specific sanitization or validation steps are provided for the content of the retrieved files beyond coordinate format checks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:33 PM
Security Audit — agent-trust-hub — maven-search