timeline

================================================================================

🔴 VERDICT: CRITICAL

This skill presents critical security vulnerabilities due to direct prompt injection and a high risk of command injection, which could lead to arbitrary code execution and data exfiltration. The reliance on an unverified script further exacerbates these risks.

Total Findings: 3

🔴 CRITICAL Findings: • Command Injection

• Line 19: The instruction Run: ${CLAUDE_PLUGIN_ROOT}/skills/timeline/scripts/timeline.php [arguments] executes a PHP script via Bash, where [arguments] are derived from user input. The allowed-tools definition Bash(${CLAUDE_PLUGIN_ROOT}/skills/timeline/scripts/timeline.php:*) confirms that arbitrary arguments can be passed to the script. Without proper sanitization of user input before constructing these arguments, an attacker could inject arbitrary shell commands (e.g., '; rm -rf /') leading to arbitrary code execution and potential system compromise. This also enables data exfiltration.

🔴 HIGH Findings: • Prompt Injection

• Line 8: The instruction Query WordPress Trac timeline for: $1 directly inserts user-controlled input ($1) into the prompt given to the LLM. An attacker could use this to inject new instructions, override the LLM's behavior, or bypass safety guidelines.

🟡 MEDIUM Findings: • Unverifiable Dependency

• Line 5: The skill executes ${CLAUDE_PLUGIN_ROOT}/skills/timeline/scripts/timeline.php. The content of this PHP script is not provided for analysis. Therefore, its security cannot be assessed, and it represents an unverifiable dependency. This significantly increases the risk associated with the command injection vulnerability.

================================================================================