The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to fetch real-time data from the x402-agent-pay.com facilitator. Several tools, such as handshake and report, take user-supplied inputs like <endpoint> and <wallet> which are sent to the service as query parameters to verify payment status and wallet authority.
[INDIRECT_PROMPT_INJECTION]: The skill consumes and processes data from remote endpoints, creating a potential surface for instructions embedded in external data to influence the agent.
Ingestion points: Data is ingested via curl responses from the facilitator and external x402 endpoints queried in SKILL.md (e.g., via the handshake or report commands).
Boundary markers: Absent. The instructions do not specify any delimiters or warnings to the agent to ignore potentially malicious instructions embedded in the external responses.
Capability inventory: The skill performs network read/write operations via curl to the facilitator and specified external endpoints. No file system write or persistent execution capabilities were identified.
Sanitization: Absent. The agent is instructed to directly quote terms (price, asset, network, etc.) and report data retrieved from the 402 responses without explicit sanitization or filtering steps.

agentpay