The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external API endpoints (e.g., health metrics, provider statistics, and audit logs) and interpolates this content into the agent's context.
Ingestion points: Data enters the agent's context through responses from endpoints such as /api/monitoring/health, /api/providers/metrics, and /api/mcp/status.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat these API responses as untrusted data.
Capability inventory: The skill utilizes shell command execution via curl to perform network operations.
Sanitization: The instructions do not specify any validation or sanitization of the JSON or text data returned by the API before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill contains a reference link to documentation hosted on the author's GitHub repository (github.com/diegosouzapw/OmniRoute). This is a reference to the vendor's own resource for configuration guidance.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill uses environment variables (OMNIROUTE_TOKEN, OMNIROUTE_KEY) to manage authentication tokens securely rather than hardcoding credentials. It communicates with a configurable backend service (OMNIROUTE_URL) or local instance (localhost:20128).

omni-resilience