skills/daxaur/openpaw/c-tracking/Gen Agent Trust Hub

c-tracking

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the ordercli command with arguments (tracking numbers and carrier names) derived from user input. Without explicit shell escaping or validation, this creates a potential surface for command manipulation.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through untrusted user data.
  • Ingestion points: User-provided tracking numbers and carrier names are used to construct CLI commands.
  • Boundary markers: None are defined to isolate tracking numbers from the command structure.
  • Capability inventory: The skill invokes the ordercli tool which performs network lookups to carrier APIs.
  • Sanitization: The skill lacks instructions to validate tracking number formats or sanitize inputs before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:44 AM
Security Audit — agent-trust-hub — c-tracking