The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute curl commands to interact with the Seren API endpoints at https://api.serendb.com. These commands facilitate data retrieval, tool discovery, and interaction with hosted services.
[DATA_EXPOSURE]: Authentication is handled via a $SEREN_API_KEY environment variable. This follows security best practices by avoiding hardcoded credentials while maintaining necessary access for API operations.
[PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it retrieves and processes content from external publishers.
Ingestion points: API responses from https://api.serendb.com/publishers and its sub-paths, which may contain third-party data.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the documentation.
Capability inventory: The skill has the ability to perform network requests (curl) and interact with database publishers (executing queries).
Sanitization: There are no instructions for sanitizing or escaping content returned by publishers before the agent processes it.

seren-publishers