shoplazza-billing

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Shoplazza CLI billing module to perform actions such as creating one-time charges, recurring subscriptions, and usage charges. These commands are executed within the context of the user's CLI environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill serves as a surface for indirect prompt injection as it ingests user-supplied data—such as prices, charge names, and IDs—to construct CLI commands. The risk is mitigated by the following design elements:
  • Ingestion points: Parameters are accepted from user input via the SKILL.md command map.
  • Boundary markers: The skill explicitly instructs the agent to restate the full transaction details and wait for a user's go-ahead before final execution, acting as a manual confirmation boundary.
  • Capability inventory: The skill has the capability to initiate financial transactions through CLI subprocess calls.
  • Sanitization: The instructions emphasize matching authoritative schemas (shoplazza schema billing) and using --jq for precise output handling, reducing the risk of data leakage or malformed command execution.
  • [DATA_EXPOSURE]: The skill includes security-conscious advice regarding authentication, specifically warning against unnecessary scope expansion (0-scope logins) that could potentially disrupt existing store access permissions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 03:06 AM