skills/mtngtools/agents/25-concise/Gen Agent Trust Hub

25-concise

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is purely instructional, defining a method for text reduction. It contains no executable scripts, shell commands, network requests, or access to sensitive files.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to process untrusted text input.
  • Ingestion points: The skill accepts "text or file to reduce" as an argument, as specified in SKILL.md.
  • Boundary markers: No specific delimiters are used to wrap the input text, nor are there instructions for the agent to ignore embedded commands within the source text.
  • Capability inventory: No high-risk capabilities such as file system writes, network exfiltration, or command execution are present in the skill instructions.
  • Sanitization: Input data is not sanitized or filtered before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:30 PM
Security Audit — agent-trust-hub — 25-concise