skills/dachent/skills/grill-me-codex/Gen Agent Trust Hub

grill-me-codex

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions and configuration files were analyzed across all threat categories, and no malicious patterns, obfuscation, or unauthorized access attempts were found. The skill operates within expected boundaries for a developer productivity tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external repository content (codebase, documentation, and issues), which serves as a potential surface for indirect prompt injection if those files contain adversarial instructions.
  • Ingestion points: Repository files, documentation, project plans, and issues (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: File searching (rg, rg --files), file reading, and conversational dialogue (SKILL.md).
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 07:58 AM
Security Audit — agent-trust-hub — grill-me-codex