The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external prediction markets which could theoretically be used for injection attacks.
Ingestion points: The agent retrieves market titles, questions, and descriptions using the agent polymarket markets and agent polymarket market commands as described in SKILL.md.
Boundary markers: Absent. The instructions do not define clear delimiters or specific instructions for the agent to ignore potential commands embedded in the external market data.
Capability inventory: The skill provides the agent with the ability to execute on-chain financial transactions, including clob-buy for placing bets, sell for closing positions, and send-native for transferring tokens.
Sanitization: Absent. There is no mention of validating or filtering the market-provided strings before the agent processes them.
[COMMAND_EXECUTION]: The skill relies extensively on the agent CLI tool to perform all operations, including account management, market analysis, and transaction execution.

polymarket-skill