acta-mathematica

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a high-level guide for journal fit and formatting. No malicious patterns, obfuscation, or unauthorized access attempts were detected.
  • [DATA_EXPOSURE]: The skill instructs the agent to reference internal files (../../resources/source-basis.md, ../../resources/official-source-map.md). These paths point to local markdown resources intended to provide context for submission guidelines, rather than sensitive system files or credentials.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided manuscripts, which constitutes an ingestion point for untrusted data. However, the skill lacks high-risk capabilities—such as automated file writes, code execution, or network exfiltration—that would allow an indirect prompt injection to compromise the system.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — acta-mathematica