flow-next-sync

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill executes a bundled script named flowctl. The execution path is strictly constructed using the plugin's root environment variables (DROID_PLUGIN_ROOT or CLAUDE_PLUGIN_ROOT), ensuring it only runs its own internal tools.
  • [DATA_EXFILTRATION] (SAFE): No network operations (curl, wget, or API calls) were detected. The data processed consists of task identifiers and repository metadata (via git), which remains local to the execution environment.
  • [PROMPT_INJECTION] (SAFE): The skill contains no instructions designed to bypass AI safety filters or override system prompts. It uses natural instructional language for workflow logic.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill ingests user-provided arguments ($ARGUMENTS). However, it includes a validation step requiring input to match specific task ID patterns (fn-*), which mitigates the risk of command injection or malicious payload interpolation.
  • [EXTERNAL_DOWNLOADS] (SAFE): No external packages or remote scripts are downloaded during the execution of this skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM