quarkus-jnosql

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external documentation and local user project files, creating a surface for potential indirect prompt injection attacks.
  • Ingestion points: Official documentation retrieved from https://docs.quarkiverse.io/quarkus-jnosql/dev/index.html and local project files (e.g., pom.xml, build.gradle, source code) during troubleshooting (SKILL.md, references/doc-navigation.md).
  • Boundary markers: The skill does not explicitly instruct the agent to use delimiters or safety guardrails when processing these external inputs.
  • Capability inventory: The skill is capable of generating Java code, modifying build configurations, and providing development advice (SKILL.md).
  • Sanitization: No specific measures for sanitizing, escaping, or validating ingested data are defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 12:38 AM