create-artifact

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a standard procedure for agents to store deliverables like research, design specs, and plans using the mcp__plugin_dh_backlog__artifact_register tool.
  • [COMMAND_EXECUTION]: No suspicious or arbitrary shell command execution was found. The skill relies on documented MCP tool invocations.
  • [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns detected. The storage of markdown content to a central backlog (GitHub issue comments) is the primary, explicitly stated purpose of the skill.
  • [PROMPT_INJECTION]: The instructions focus on tool usage and documentation standards without attempting to override agent safety protocols or system behavior.
  • [OBFUSCATION]: No hidden content, encoded strings, or evasive techniques were identified in the skill documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 11:39 PM
Security Audit — agent-trust-hub — create-artifact