payping
Warn
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The instructions recommend installing the
payping-mcppackage usinguvx, which involves downloading and executing code from an external registry. This behavior is associated with the skill's primary purpose of providing PayPing integration.\n- [EXTERNAL_DOWNLOADS]: The skill documentation points to external dependencies (the MCP server) that are not bundled with the skill itself.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the PayPing API which could contain malicious instructions designed to influence the agent's behavior.\n - Ingestion points: Data is retrieved from tools such as
payping_list_transactions(description field) andpayping_get_customer(memo field) in SKILL.md.\n - Boundary markers: The instructions lack explicit boundary markers or warnings to the agent regarding potential instructions embedded in API data.\n
- Capability inventory: The skill has the ability to create and send invoices and products, representing a risk if the agent is manipulated by external data.\n
- Sanitization: There is no mention of data validation or sanitization for content retrieved from external API calls.
Audit Metadata