The Agent Skills Directory

[PROMPT_INJECTION] (LOW): Indirect prompt injection surface via the EigenExplorer API. The skill processes external blockchain data (e.g., AVS names, operator descriptions) that could contain malicious instructions designed to influence agent behavior.
Ingestion points: API responses from api.eigenexplorer.com and api-holesky.eigenexplorer.com processed in scripts/avs-api.js and SKILL.md.
Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions within the fetched data.
Capability inventory: Shell execution via curl and network access via the axios library.
Sanitization: Absent; the agent is explicitly instructed to format and present the raw API results to the user.
[EXTERNAL_DOWNLOADS] (LOW): The skill performs network requests to api.eigenexplorer.com. While this domain is specific to the skill's primary purpose, it is not on the predefined list of whitelisted domains.
[COMMAND_EXECUTION] (SAFE): Use of curl is instructed for legitimate data retrieval from the service provider.

eigen-avs