skill-chain-prompts

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill implements an orchestration layer that processes YAML-based workflow definitions, which introduces a potential indirect prompt injection surface.\n
  • Ingestion points: Workflow definitions provided in assets/chains/ and custom YAML blocks input by users.\n
  • Boundary markers: There are no explicit delimiters or specific instructions to isolate and ignore embedded commands within the workflow steps.\n
  • Capability inventory: The skill is designed to invoke multiple other system skills (e.g., /api-design-patterns, /deployment-cicd) sequentially.\n
  • Sanitization: No input validation or filtering of YAML fields such as skill or args is implemented.\n- [NO_CODE]: The skill consists solely of markdown and YAML configuration files. It does not distribute any executable scripts or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:10 PM