merchant-feed-audit
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Google Merchant API (Step 1, Step 3, Step 6), including product attributes like titles and descriptions. Maliciously crafted product data could attempt to influence the agent's behavior during the audit process.\n
- Ingestion points: API responses from merchantapi.googleapis.com containing product details and issue reports (specified in references/merchant-api.md).\n
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the processed data.\n
- Capability inventory: The skill utilizes shell commands (curl) for API interactions (specified in references/merchant-api.md).\n
- Sanitization: No explicit sanitization or validation of the external API content is defined before processing.\n- [COMMAND_EXECUTION]: The skill provides instructional examples using curl to interact with the Google Merchant API (described in references/merchant-api.md). These commands are intended for auditing and account management and target official Google endpoints.\n- [EXTERNAL_DOWNLOADS]: The skill references and interacts with the official Google Merchant API (merchantapi.googleapis.com). These references target a well-known service and are documented neutrally as part of the skill's core auditing functionality.
Audit Metadata