java-code-review

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute local validation commands, such as compilation, test runs, and static analysis, which are standard for the development workflow it supports.- [PROMPT_INJECTION]: The skill's primary function involves processing untrusted source code and git diffs, which constitutes an indirect prompt injection attack surface.
  • Ingestion points: The agent reads Java files, git status, and diff outputs from the local repository as specified in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or markers to separate the reviewed code from the system instructions.
  • Capability inventory: The agent has capabilities to read files, write a report to review.md, and execute shell commands for build and test validation.
  • Sanitization: There are no explicit sanitization or filtering steps for the untrusted code content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 02:32 AM
Security Audit — agent-trust-hub — java-code-review