java-review

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill utilizes the $ARGUMENTS placeholder to ingest untrusted Java code directly into its instruction prompt without employing delimiters or sanitization. This creates a surface for indirect prompt injection where instructions embedded in the code could override the agent's intended behavior.
  • Ingestion point: $ARGUMENTS variable in SKILL.md.
  • Boundary markers: Absent. User content is concatenated directly with system instructions.
  • Capability inventory: No file system access, network operations, or tool executions are defined in the skill body.
  • Sanitization: No input validation or filtering is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 11:17 PM
Security Audit — agent-trust-hub — java-review