The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the bash tool to execute curl commands for all API interactions. While necessary for its purpose, executing shell commands is a powerful capability.
[EXTERNAL_DOWNLOADS]: Fetches data from an external API endpoint (polyhub.skill-test.bedev.hubble-rpc.xyz) to retrieve market tags, trader rankings, and statistics.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from an external API and uses it to perform multi-step analysis and make recommendations to the user.
Ingestion points: Data enters the agent context through several API endpoints including /api/v1/traders-v2/ and /api/v1/traders/by-address (SKILL.md).
Boundary markers: The instructions do not define delimiters or specific safety instructions for the agent when parsing the JSON responses from the API.
Capability inventory: The skill has the capability to execute shell commands via bash for network requests; no file system write or persistent execution capabilities were found.
Sanitization: There is no evidence of sanitization or validation of the API's content before the agent interprets it to identify 'smart money' or 'profitable traders'.

polyhub_discover