task-generator

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to automate the creation of markdown task files. It operates on local files within the project structure (e.g., requirements.md) and outputs structured text to a tasks folder.
  • [COMMAND_EXECUTION]: No shell commands, subprocess calls, or system-level execution patterns were identified in the instructions or references.
  • [DATA_EXFILTRATION]: There are no network operations (curl, wget, or API calls). The skill does not transmit data externally.
  • [PROMPT_INJECTION]: The instructions contain strict guidelines for the agent to follow project rules and requirements without any attempts to bypass safety filters or override system prompts.
  • [EXTERNAL_DOWNLOADS]: The skill relies on a local dependency (nextstage-harness) and does not download or install external packages from remote registries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 10:10 PM
Security Audit — agent-trust-hub — task-generator