oracle-grillme

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes project files and documentation to drive its Socratic interrogation loop, creating an indirect prompt injection surface where malicious content in the codebase could influence agent behavior.\n
  • Ingestion points: Local source code files, CONTEXT.md, and ADR files in docs/adr/.\n
  • Boundary markers: No specific boundary markers or instructions to ignore embedded directives are provided when the agent reads file content.\n
  • Capability inventory: The skill uses file system read capabilities for codebase exploration and file system write capabilities for updating documentation and ADRs.\n
  • Sanitization: No sanitization or escaping of ingested file content is specified prior to interpolation into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 01:53 AM
Security Audit — agent-trust-hub — oracle-grillme