naval-architect-expert

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides detailed instructions for acting as a naval architect expert. No prompt injection techniques, such as attempts to bypass safety filters or ignore prior instructions, were detected.- [SAFE]: The agent is instructed to read from a local data file (data/doc-intelligence/worked_examples.jsonl) to retrieve engineering examples. This data access is restricted to the skill's own directory and does not expose sensitive system credentials.- [SAFE]: The skill utilizes a specialized Python library (digitalmodel) for domain-specific engineering calculations. These operations are performed within the scope of the provided modules and do not involve arbitrary shell command execution or unauthorized system access.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 03:41 PM
Security Audit — agent-trust-hub — naval-architect-expert