Skills
Navigate
skills/compozy/kb/cy-create-tasks/Gen Agent Trust Hub

cy-create-tasks

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external requirements files to drive task generation, creating an attack surface for instructions embedded in source documents. Ingestion points: _prd.md, _techspec.md, and ADR files in the .compozy/tasks/ directory. Boundary markers: Absent. Capability inventory: Writing task files and executing the compozy CLI tool. Sanitization: Absent.
  • [COMMAND_EXECUTION]: The skill executes the compozy tasks validate command to verify the generated task graph, which is a standard functional requirement for this tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 01:24 AM