api-design

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_CONTEXT_INJECTION]: The file scripts/create-openapi-spec.md utilizes the shell execution syntax (e.g., !grep, !date) to automatically inspect the local project environment. It searches for route definitions in Python/TypeScript files and configuration variables in .env files to pre-populate OpenAPI templates. These operations are restricted to project metadata discovery and do not involve data exfiltration or high-risk command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied arguments ($ARGUMENTS) to define API names and titles in generated specifications. While this creates a surface for indirect prompt injection if the generated output is subsequently processed by another automated agent, the risk is minimal as the skill is designed for developer-assisted documentation generation rather than autonomous system operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 05:22 AM
Security Audit — agent-trust-hub — api-design