pp-3cx-xapi

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the 3cx-xapi-pp-cli and 3cx-xapi-pp-mcp tools from the author's NPM and GitHub repositories using npx and go install. These are vendor-owned resources.\n- [COMMAND_EXECUTION]: The skill functions by executing shell commands via the 3cx-xapi-pp-cli binary to perform administrative and auditing tasks on 3CX PBX instances.\n- [DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> flag that allows the agent to route command outputs to an arbitrary external URL endpoint.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it ingests untrusted data from external 3CX phone systems which could contain malicious instructions.\n
  • Ingestion points: Reads configuration details, log entries, and reporting data from the 3CX PBX using subcommands such as users list and activity-log get-logs.\n
  • Boundary markers: The skill instructions do not provide clear delimiters or warnings to the agent to disregard instructions embedded within the ingested data.\n
  • Capability inventory: The skill possesses powerful command execution capabilities to modify PBX configurations, create users, and manage security settings.\n
  • Sanitization: There is no mention of sanitizing, validating, or filtering the data retrieved from the PBX before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 09:18 AM
Security Audit — agent-trust-hub — pp-3cx-xapi