recsys-pipeline-architect

Warn

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install components via 'npx skills add' from an external repository (mturac/recsys-pipeline-architect) that is not identified as a recognized official service or author-verified source.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates a code generation workflow using external data, creating an attack surface for indirect prompt injection.
  • Ingestion points: User-provided use case clarifications and input context in SKILL.md.
  • Boundary markers: Absent; the instructions do not define delimiters for user data.
  • Capability inventory: Generation of runnable code scaffolds (SKILL.md).
  • Sanitization: Absent; no validation requirements are defined for the interpolated user context.
  • [DYNAMIC_EXECUTION]: The skill instructions direct the agent to generate functional code scaffolds in multiple languages (TypeScript, Go, Python) based on user-specified requirements, which represents a risk if the generation process is influenced by malicious input.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 12, 2026, 03:41 PM
Security Audit — agent-trust-hub — recsys-pipeline-architect