gumroad
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from the Gumroad API that could contain malicious instructions designed to influence the agent's behavior.\n
- Ingestion points: Data retrieved from
https://api.gumroad.com/v2/sales,https://api.gumroad.com/v2/products, andhttps://api.gumroad.com/v2/user(processed viacurlinSKILL.md).\n - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent processes the retrieved API content.\n
- Capability inventory: The skill possesses the capability to modify store state, including creating (
POST /v2/products), updating (PUT /v2/sales/.../mark_as_shipped), and deleting products (mentioned in the 'When to Use' section).\n - Sanitization: No sanitization or validation of the API-returned data is performed before the agent acts upon it.\n- [COMMAND_EXECUTION]: The skill utilizes
curlfor API interactions and includes a vendor-specific diagnostic command (zero doctor). These operations involve well-known service domains and legitimate vendor resources, consistent with the skill's primary purpose.
Audit Metadata