workflow-seed-test-data
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external project configuration (
docs/project-config.json) and manages "realistic data" for seeding, which creates a surface for indirect prompt injection attacks. - Ingestion points: Processes project configuration files and seeder scenario data at runtime.
- Boundary markers: No specific delimiters or warnings to ignore embedded instructions are defined in the workflow instructions.
- Capability inventory: The skill can execute local scripts, spawn subagents, and write new seeder code to the filesystem.
- Sanitization: The skill does not describe any specific sanitization or filtering logic for the data it processes.
- [COMMAND_EXECUTION]: The skill directs the agent to execute a local Node.js script (
node .claude/scripts/lib/workflow-skill-contract.cjs) to regenerate and synchronize workflow definitions. - [DYNAMIC_EXECUTION]: The skill dynamically identifies, loads, and executes additional skills by following relative paths and instructions defined in a local registry file (
.claude/workflows.json).
Audit Metadata