prompt-atom-formalization

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user-supplied source text to extract and formalize prompt atoms, creating an indirect prompt injection surface (Category 8).
  • Ingestion points: Source text input (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or ignore instructions for the input text.
  • Capability inventory: The skill is authorized to read and create files on the local filesystem for registry maintenance.
  • Sanitization: The workflow focuses on verbatim extraction and minimal restatement without active filtering for malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 02:18 AM
Security Audit — agent-trust-hub — prompt-atom-formalization