infrastructure-enumeration
Warn
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes numerous CLI tools (e.g., nmap, snmpwalk, dnsrecon) and specifically requires elevated privileges via
sudo mountto interact with NFS exports. - [DATA_EXFILTRATION]: Includes commands to attempt retrieval of sensitive files like
/etc/passwdvia TFTP and instructions to store discovered credentials and vulnerability evidence in local files. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by processing untrusted data from network services. (1) Ingestion points: Tool outputs from network probes (DNS, LDAP, SNMP) described in
SKILL.md. (2) Boundary markers: None present; external data is not delimited or marked as untrusted. (3) Capability inventory: Subprocess execution of network tools across all sections and local file writes to theengagement/directory. (4) Sanitization: No evidence of data sanitization or validation of tool outputs before processing.
Audit Metadata