optimize-md

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes untrusted markdown content from files provided as arguments. There are no explicit boundary markers to isolate the file content from the agent's instructions, creating a surface for indirect prompt injection if the file contains instructions. Evidence:
  • Ingestion points: Workflow Step 1 in SKILL.md reads content from a user-provided file path.
  • Boundary markers: Absent.
  • Capability inventory: The skill has the ability to read and rewrite files in-place.
  • Sanitization: Absent.
  • Data Exposure & Exfiltration (SAFE): The skill performs local file read/write operations for the purpose of document optimization. No network activity, hardcoded credentials, or exfiltration patterns were detected.
  • Command Execution (SAFE): The skill does not execute system commands or shell scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 05:25 AM