billing-verification
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from the Credyt API (such as product names, event types, and wallet details) which could be used to host malicious instructions.
- Ingestion points: The agent calls
credyt:list_productsandcredyt:get_product(SKILL.md), andcredyt:get_walletandcredyt:get_event(references/procedure.md). - Boundary markers: No delimiters or specific 'ignore embedded instructions' warnings are used when presenting API data to the user or agent.
- Capability inventory: The skill has the ability to write data via
credyt:create_customer,credyt:create_adjustment(funding wallets), andcredyt:submit_events(usage reporting). - Sanitization: There is no evidence of filtering, escaping, or validation of the content retrieved from the external API before it is interpolated into the agent's context.
Audit Metadata