markdownlint

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to verify the presence of markdownlint-cli and to execute validation or auto-fix operations on project files.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the markdownlint-cli package from the public NPM registry if it is not already available on the host system.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted markdown files from the project directory, which could contain instructions intended to influence the agent's behavior during the reporting of validation errors.
  • Ingestion points: Markdown files and directories passed to the markdownlint command as described in SKILL.md.
  • Boundary markers: Absent; there are no specific delimiters or instructions used to prevent the agent from following instructions embedded within the files being linted.
  • Capability inventory: Shell command execution via markdownlint and npm.
  • Sanitization: Absent; error reports and rule violations are extracted directly from the tool output and presented in the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:27 AM
Security Audit — agent-trust-hub — markdownlint