specsfy-specialist-data-modeling

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate instructions for analyzing and modeling data within a software project. It emphasizes understanding existing code (migrations, models, schemas) before proposing changes and follows established documentation patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data by reading project source files to perform its task, which is the primary intended purpose of the skill. While this creates a theoretical surface for indirect instructions, the skill lacks dangerous capabilities such as network access, arbitrary code execution, or administrative privilege acquisition.
  • Ingestion points: Reads stack configuration, migrations, schemas, models, and tests (SKILL.md, Step 1).
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Identifies entities, generates modeling scenarios, and writes documentation to .specsfy/DATABASE.md (SKILL.md).
  • Sanitization: No explicit sanitization of the ingested code content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:33 PM
Security Audit — agent-trust-hub — specsfy-specialist-data-modeling