performing-security-audits
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's configuration (
SKILL.md) requests broad permissions for arbitrary shell command execution via theBashtool with a wildcard (cmd:*). This capability is intended for running security tools such as nmap or nessus as described in the scripts documentation, but it grants the agent the ability to execute any command on the host environment. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, such as third-party codebases and infrastructure configurations, for security auditing purposes. This creates a significant surface for indirect prompt injection attacks.
- Ingestion points: The skill accepts code, configuration files, and API endpoints for analysis as described in the
How It Workssection ofSKILL.md. - Boundary markers: The instructions do not define explicit delimiters or security boundaries to ensure the agent differentiates between its own instructions and the content being audited.
- Capability inventory: The skill possesses high-privilege capabilities including full file system access (Read, Write, Edit, Grep, Glob) and arbitrary shell command execution (
Bash(cmd:*)). - Sanitization: There is no evidence of sanitization, validation, or filtering of the audited content before it is processed by the agent's logic.
Audit Metadata