skills/evansking/openclaw-shared/qmd/Gen Agent Trust Hub

qmd

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the 'qmd' package from a public registry using 'bun install -g qmd'. This is a standard procedure for installing the required utility.
  • [COMMAND_EXECUTION]: The skill utilizes the 'qmd' binary to perform various local operations, including indexing folder contents ('qmd init'), updating the search index ('qmd update'), and performing keyword or semantic searches ('qmd search', 'qmd vsearch').
  • [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it reads and processes user-provided markdown files to provide search results to the agent.
  • Ingestion points: Content is retrieved via 'qmd search' and 'qmd get' commands.
  • Boundary markers: The instructions do not define specific delimiters for the retrieved file content.
  • Capability inventory: The skill allows execution of the 'qmd' binary and reading of local files.
  • Sanitization: There is no explicit sanitization of the file content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 12:12 AM
Security Audit — agent-trust-hub — qmd