The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the curl command to interact with the maskdb API for listing databases, schemas, and retrieving data. It also references a zero doctor command for troubleshooting connection issues.
[EXTERNAL_DOWNLOADS]: The skill fetches metadata and database row content from the external domain api.maskdb.ai.
[PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection by processing data from external databases.
Ingestion points: Untrusted data enters the agent's context when it executes queries and retrieves row content via the api.maskdb.ai/v1/databases/<database>/query endpoint as described in SKILL.md.
Boundary markers: The skill does not provide delimiters or specific instructions to the agent to treat the retrieved database content as untrusted or to ignore any instructions embedded within the data.
Capability inventory: The agent is capable of executing network requests via curl and running the zero doctor diagnostic tool.
Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved database content before it is processed by the agent.

maskdb