skills/changeflowhq/skills/qmd/Gen Agent Trust Hub

qmd

Fail

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSPERSISTENCEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONTIME_DELAYED_CONDITIONAL
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill setup (setup/README.md) and diagnostic script (scripts/doctor.sh) suggest installing the Bun runtime via a shell script from its official domain (https://bun.sh/install). It also installs the qmd tool directly from the tobi/qmd GitHub repository using the Bun package manager.
  • [PERSISTENCE]: The skill includes a macOS LaunchAgent template (templates/launchd.plist) and instructions for its installation to perform daily background embedding refreshes. It also recommends configuring PostToolUse hooks in the agent's settings.json to trigger real-time index updates after file modifications.
  • [DYNAMIC_EXECUTION]: The diagnostic script scripts/doctor.sh uses the eval command to perform status checks on system dependencies. This allows the script to dynamically verify the presence of tools like Bun, SQLite, and the qmd binary in the user's environment.
  • [TIME_DELAYED_CONDITIONAL]: The automation strategy relies on a launchd job scheduled to run daily at midnight to regenerate embeddings. This time-gated execution manages resource-heavy indexing tasks outside of active working hours.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to search and retrieve content from a local collection of markdown files, which represents a potential attack surface.
  • Ingestion points: Markdown content is ingested through search and query commands (qmd search, qmd vsearch, qmd query) from files in the user's project directory as specified in SKILL.md and setup/README.md.
  • Boundary markers: There are no explicit markers or prompt instructions to isolate search results from the agent's primary instructions or to treat the retrieved content as untrusted.
  • Capability inventory: The agent has access to Bash, Read, Write, and Edit tools, which could be misused if search results contain malicious instructions that the agent executes.
  • Sanitization: The skill does not perform sanitization or validation of the indexed markdown content before presenting it to the agent.
  • [COMMAND_EXECUTION]: The skill frequently executes external commands, including the qmd CLI for search and indexing, and system utilities like launchctl, brew, and fswatch for environment management and automation.
Recommendations
  • HIGH: Downloads and executes remote code from: https://bun.sh/install - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 8, 2026, 11:41 PM