skills/mthds-ai/skills/mthds-inputs/Gen Agent Trust Hub

mthds-inputs

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the mthds-agent CLI for version checking, schema extraction (pipelex inputs pipe), and pipeline execution (pipelex run pipe). This is essential for integrating with the MTHDS ecosystem.\n- [REMOTE_CODE_EXECUTION]: The skill provides Python code templates using libraries like reportlab, python-docx, and openpyxl to generate synthetic PDF, Word, and Excel documents. These scripts are generated and executed locally at runtime to create test inputs.\n- [EXTERNAL_DOWNLOADS]: The skill directs users to install the mthds NPM package (from the verified vendor mthds-ai) and standard Python libraries. It also references a public fallback document from w3.org, a well-known and trusted service.\n- [DATA_EXFILTRATION]: The skill performs file and folder enumeration to locate and copy user-provided files into its workspace. While this involves reading local data, it is performed in response to explicit user input to populate pipeline parameters.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. \n
  • Ingestion points: Reads content from user-provided .txt and .md files in Step E: Build Content Objects.\n
  • Boundary markers: None; the raw file content is interpolated directly into the inputs.json structure.\n
  • Capability inventory: Ability to execute shell commands via the mthds-agent CLI and perform file system writes.\n
  • Sanitization: No escaping or validation is performed on the text content read from external files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 03:22 PM