java-junit

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to perform local verification using build tool commands such as mvn test or gradle test. It also references the use of local Python scripts like scripts/validate-skills.py for skill management tasks.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it is designed to ingest and process user-provided Java source and test files.
  • Ingestion points: Java code and test classes supplied by the user (documented in SKILL.md).
  • Boundary markers: Absent; there are no specific instructions or delimiters provided to help the agent ignore malicious instructions potentially embedded within code comments or strings.
  • Capability inventory: The agent is empowered to execute shell commands via build tools and local management scripts.
  • Sanitization: No evidence of validation, escaping, or filtering of the external code content is present in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 04:53 PM
Security Audit — agent-trust-hub — java-junit