skills/mtngtools/agents/50-concise/Gen Agent Trust Hub

50-concise

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts external text or files as input for reduction, creating a surface for indirect prompt injection. However, since the skill has no dangerous tools (no file writing, network access, or command execution), the risk is minimal.
  • Ingestion points: User-provided text or file content through the 'argument-hint' parameter.
  • Boundary markers: None defined in the main SKILL.md file.
  • Capability inventory: No high-risk capabilities or tools are invoked.
  • Sanitization: No input sanitization or validation is specified in the instruction.
  • [SAFE]: The primary purpose is text processing, and the reference to a local method file is standard for organized skill sets. No suspicious or obfuscated code was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:30 PM
Security Audit — agent-trust-hub — 50-concise