proofreader-api

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to execute a provided Node.js script to inventory the workspace targets.
  • Evidence: Procedures in SKILL.md instruct the agent to run node scripts/find-proofreader-targets.mjs . to find frontend files and Proofreader API markers.
  • [PROMPT_INJECTION]: The skill's workspace scanning functionality creates a surface for indirect prompt injection.
  • Ingestion points: The find-proofreader-targets.mjs script reads arbitrary file content from the workspace using fs.readFileSync.
  • Boundary markers: Absent. No specific instructions are provided to the agent to separate the script output from potential instructions inside the scanned files.
  • Capability inventory: The skill can read project files, execute scripts, and perform code implementation tasks.
  • Sanitization: Absent. The script processes file contents directly without filtering or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 03:18 PM
Security Audit — agent-trust-hub — proofreader-api