skills/mindrally/skills/meta-prompt/Gen Agent Trust Hub

meta-prompt

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [Prompt Injection] (SAFE): No direct prompt injection patterns (overrides, bypasses, or 'ignore instructions') were detected in the skill instructions.
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze external data (AI responses and solution trajectories).
  • Ingestion points: Evaluation templates in SKILL.md (e.g., 'Response Quality Evaluator') are designed to process candidate responses.
  • Boundary markers: Absent; the templates do not define delimiters or specific warnings to ignore instructions embedded in the analyzed content.
  • Capability inventory: None; the skill contains no scripts or tools for file writing, network access, or command execution.
  • Sanitization: Absent; there is no mention of filtering or escaping content before evaluation.
  • [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded secrets, or network communication protocols were found.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill contains no code, package definitions, or remote script download patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:49 PM