most-important-thing-in-investing-howard-marks

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill consists of instructional markdown files and quotes designed to guide an AI agent in investment reasoning based on Howard Marks' principles. No hidden code, obfuscation, or sensitive data access was identified.
  • [EXTERNAL_DOWNLOADS]: The README suggests using a CLI tool (npx skills add ...) for installation. This refers to the author's own distribution mechanism and represents standard vendor functionality for skill deployment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided investment queries. While it does not utilize explicit boundary markers for this input, the skill lacks executable capabilities (such as network access, file writing, or shell command execution) that could be leveraged for an exploit. The design is limited to providing structured textual analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 09:54 AM
Security Audit — agent-trust-hub — most-important-thing-in-investing-howard-marks