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

cy-create-tasks

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run the compozy validate-tasks CLI command. This is a tool provided by the skill's author used to verify the integrity of the generated task files.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes requirements from external files into the agent context.\n
  • Ingestion points: Reads _prd.md, _techspec.md, and ADR markdown files from the .compozy/tasks/ directory.\n
  • Boundary markers: None identified; the instructions do not mandate delimiters or warnings to ignore instructions within the requirement files.\n
  • Capability inventory: The agent can create/modify files (_tasks.md, task_NN.md) and execute shell commands (compozy).\n
  • Sanitization: No input validation or sanitization logic is described for the content of the requirements documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 12:15 AM
Security Audit — agent-trust-hub — cy-create-tasks