construction-docs

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted engineering design data (BlueprintPackage) that could contain malicious instructions. 1. Ingestion points: The skill parses P&ID and SLD drawings and CalculationRecord outputs mentioned in SKILL.md. 2. Boundary markers: No explicit delimiters or warnings to ignore embedded instructions in the input data are present. 3. Capability inventory: The skill is allowed access to Bash, Read, Grep, and Glob tools. 4. Sanitization: No sanitization or validation of the input engineering data is provided.
  • [SAFE]: The skill adheres to professional engineering standards by requiring Licensed Professional Engineer (PE) review for all generated documents, which serves as a critical human-in-the-loop safety measure.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:15 PM
Security Audit — agent-trust-hub — construction-docs