wp-project-triage

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted metadata from repository files (such as WordPress plugin headers, package.json fields, and theme.json content) and includes them in a structured report. This creates a surface for indirect prompt injection if an attacker-controlled repository contains malicious instructions within these metadata fields.\n
  • Ingestion points: scripts/detect_wp_project.mjs reads various repository files including PHP headers and JSON configuration files using fs.readFileSync.\n
  • Boundary markers: The output is structured as JSON, but there are no explicit delimiters or instructions provided to the agent to disregard embedded commands in the data report.\n
  • Capability inventory: The agent is instructed in SKILL.md to use the report to determine workflow guardrails and execute shell commands such as npm run lint or composer install.\n
  • Sanitization: Data is extracted and trimmed but not sanitized for prompt injection patterns before inclusion in the final JSON output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:16 AM
Security Audit — agent-trust-hub — wp-project-triage