skills/seikaikyo/dash-skills/openspec/Gen Agent Trust Hub

openspec

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill instructs the installation of the global npm package @fission-ai/openspec@latest. The organization fission-ai is not on the trusted sources list, making this an unverifiable dependency.
  • [COMMAND_EXECUTION] (LOW): The skill utilizes CLI commands (dash spec, openspec) to interact with the file system. While these are part of the intended functionality, they represent a mechanism for local command execution.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes external markdown files (specs and changes) created by users. While it reads these files for display and validation, the current capabilities are limited to local workflow management, presenting a low surface for malicious influence.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:25 PM