tw-research-methodology-designer

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown files that guide the AI's logic for academic consulting. It does not contain any executable scripts (.py, .js, .sh) or active command triggers.
  • [DATA_EXPOSURE]: No access to sensitive system files, environment variables, or hardcoded credentials was found. The skill only reads its own local reference files provided within the package.
  • [REMOTE_CODE_EXECUTION]: The skill does not perform network operations, download external content, or install third-party packages. It contains no patterns of dynamic code execution or remote script invocation.
  • [PROMPT_INJECTION]: The instructions use standard pedagogical framing to define the agent's persona as a methodology expert. There are no attempts to bypass safety filters or ignore prior instructions.
  • [COMMAND_EXECUTION]: While the YAML frontmatter includes 'Bash' in allowed-tools (limiting the agent's scope), the skill itself does not invoke any shell commands or perform high-privilege operations.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 11:16 AM