skills/cpaikr/dsdai/dart-dsd/Gen Agent Trust Hub

dart-dsd

Pass

Audited by Gen Agent Trust Hub on Nov 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for the agent to download and install the dsd CLI tool from the author's public GitHub repository (https://github.com/cpaikr/dsdai/releases). These instructions are transparent and emphasize using official releases and checksum verification.
  • [COMMAND_EXECUTION]: The skill relies on two command-line tools: the dsd CLI for document processing and the gh (GitHub) CLI for reporting issues. Both are standard for developer-oriented tools, and the instructions require explicit user approval before performing actions like filing GitHub issues.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external .dsd files which may contain untrusted data.
  • Ingestion points: Data enters the agent's context when reading .dsd files (specifically contents.xml) through the dsd CLI tool as described in SKILL.md and references/reading.md.
  • Boundary markers: The skill uses a dedicated CLI tool that returns structured JSON or formatted text, providing a layer of abstraction between the raw file content and the agent's prompt.
  • Capability inventory: The skill possesses capabilities for file system read/write and execution of the dsd and gh command-line tools.
  • Sanitization: The instructions mandate quoting figures and text directly from the tool's output and require post-edit verification using dsd check and dsd diff to ensure no unintended changes were made.
  • [DATA_EXFILTRATION]: The skill explicitly instructs the agent to treat documents as confidential, process them locally, and avoid uploading them to external services or shared locations.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 18, 2026, 08:22 AM