The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use curl commands to interact with the SerenDB API for managing projects, branches, databases, and roles.
[EXTERNAL_DOWNLOADS]: The skill performs network operations targeting api.serendb.com to fetch configuration, metadata, and database query results.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted data from a database and API responses that could contain malicious instructions.
Ingestion points: Data ingested through API responses and SQL query results from api.serendb.com (SKILL.md).
Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore instructions embedded in the processed data.
Capability inventory: Network operations via curl and database management/querying capabilities (SKILL.md).
Sanitization: Absent. There is no mention of sanitizing or validating the content retrieved from the database before the agent processes it.

seren-db