skills/ruvnet/ruflo/create-plugin/Gen Agent Trust Hub

create-plugin

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill scaffolds plugin files using user-supplied names and descriptions, creating an indirect prompt injection surface.
  • Ingestion points: User-provided plugin names and descriptions are used to populate generated files like SKILL.md and README.md.
  • Boundary markers: The generation logic does not employ delimiters to isolate user-provided text from template instructions.
  • Capability inventory: The skill leverages Bash, Write, and Edit tools to create executable shell scripts and project files.
  • Sanitization: No validation or escaping of user-supplied input is specified before it is written to the file system.
  • [COMMAND_EXECUTION]: The skill generates a shell script (smoke.sh) and explicitly instructs the user to execute it via Bash for project verification.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 06:53 PM
Security Audit — agent-trust-hub — create-plugin