cv-craft

Warn

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the shell command npx --yes md-to-pdf to convert resumes. This command includes the --no-sandbox flag which disables the Chrome security sandbox, increasing the risk if the tool processes malicious content.
  • [REMOTE_CODE_EXECUTION]: The skill uses npx to dynamically download and execute the md-to-pdf package from the NPM registry at runtime.
  • [EXTERNAL_DOWNLOADS]: The PDF generation process triggers a download of the Chromium browser (approximately 170MB) during its first run.
  • [PROMPT_INJECTION]: The skill processes Job Descriptions (JDs) from untrusted sources (text, URLs, or files) to tailor resumes.
  • Ingestion points: Job Descriptions from user text, files, or URLs.
  • Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are provided to the agent.
  • Capability inventory: The skill can execute shell commands via npx, read local files, and write files to the system.
  • Sanitization: No validation or sanitization of the JD content is performed before the agent processes it.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 7, 2026, 02:42 PM
Security Audit — agent-trust-hub — cv-craft