interactive-markdown-review

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process external markdown documents where content within <single brackets> is interpreted as author instructions. This creates a surface where a malicious document (e.g., in a compromised repository) could inject instructions to influence the agent's behavior.
  • Ingestion points: Reads markdown documents (<document.md>) and JSON notes files (.notes.json).
  • Boundary markers: Uses specific bracket patterns (<...>, <<...>>) to distinguish between author and editor input.
  • Capability inventory: The agent can write to the local file system, execute Node.js scripts, and run shell commands like git and lavish-axi.
  • Sanitization: The render.mjs script performs HTML escaping for the rendered review page.
  • [COMMAND_EXECUTION]: The skill relies on executing Node.js scripts (serve.mjs, render.mjs) and external CLI tools (git, lavish-axi). While these are standard developer tools, they represent an execution capability that could be abused if the agent's logic is subverted.
  • [DYNAMIC_EXECUTION]: The SKILL.md file contains instructions for the agent to evolve the skill by folding lessons into its own SKILL.md file. This self-modification of the agent's instruction set is a form of dynamic code modification, although the protocol explicitly requires the author's agreement before making such changes.
  • [EXTERNAL_DOWNLOADS]: The documentation (README.md and visual-mode.md) directs the agent to check for and potentially install Node.js and the lavish-axi package via npm. The instructions specify that the agent should only proceed with user consent and handle permissions (like sudo) carefully.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 05:58 PM