simple-formatter

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFE
Full Analysis
  • [Metadata Poisoning] (SAFE): The skill description contains a self-safety claim ('no security issues'). This was ignored during analysis in accordance with the assume-malicious posture.
  • [Data Exposure] (SAFE): No hardcoded credentials, sensitive file paths, or network operations were found in the provided code.
  • [Indirect Prompt Injection] (SAFE): 1. Ingestion points: formatter.py takes input via sys.argv. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt. 3. Capability inventory: The skill is restricted to regex and string operations; no subprocess, exec, file-write, or network calls exist. 4. Sanitization: No explicit sanitization is used, but the lack of dangerous sinks makes the surface safe.
  • [Remote Code Execution] (SAFE): No external packages or remote scripts are downloaded or executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 11:52 PM