grill-me

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a directive to "explore the codebase" to resolve questions. This introduces an indirect prompt injection surface where untrusted data from the repository could influence agent behavior.
  • Ingestion points: Local codebase exploration as requested in SKILL.md.
  • Boundary markers: Absent; there are no instructions to ignore embedded commands or delimiters for codebase content.
  • Capability inventory: Relies on the agent's inherent file reading and search capabilities.
  • Sanitization: Absent; the skill does not specify validation or sanitization of content found in the codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 07:44 AM
Security Audit — agent-trust-hub — grill-me