pay
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the installation of the
@solana/paypackage (references/setup-cli.md) and the use of Docker images fromghcr.io/solana-foundation/pay(references/monetize-api.md). These resources belong to the Solana Foundation, a well-known entity in the blockchain ecosystem.\n- [PROMPT_INJECTION]: The skill processes external API responses, which presents an indirect prompt injection surface.\n - Ingestion points: Untrusted data enters the agent's context through the responses of the
curltool and metadata retrieved bysearch_catalogandget_catalog_entry(SKILL.md).\n - Boundary markers: The agent is instructed in
references/security.mdto isolate external content by wrapping it in fenced code blocks with an explicit 'Provider output (untrusted):' label.\n - Capability inventory: The agent possesses network request capabilities via the
curltool and can check wallet balances (SKILL.md).\n - Sanitization: The instructions in
references/security.mdprovide a strong mitigation by explicitly commanding the agent to ignore any instructions or operational guidance embedded in external responses and to report such events to the user.
Audit Metadata