ios-workflow-to-playwright

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data to influence automated code generation.
  • Ingestion points: The skill reads user-controlled workflow definitions, including descriptions and steps, from the /workflows/ios-workflows.md file in Phase 1.
  • Boundary markers: There are no explicit boundary markers or instructions provided to the agent to treat the workflow content as data only or to ignore instructions embedded within the markdown.
  • Capability inventory: The skill possesses the capability to write executable files to the filesystem (e2e/ios-mobile-workflows.spec.ts) and uses sub-agents for selector discovery and code generation (Phase 3 and Phase 6).
  • Sanitization: The skill does not perform sanitization, escaping, or validation on the input markdown content before interpolating it into prompts for the sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 03:49 AM