The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines alerts that ingest data from external telemetry and database sources and interpolate it into action configurations.\n
Ingestion points: Results from orchestrationQuery and storageQuery, and telemetry fields such as executionTitleOrErrorMessage defined in SKILL.md and references/scopes-and-thresholds.md.\n
Boundary markers: Absent. The templating system described in references/alert-lifecycle.md (e.g., {{event.value}}) does not implement visible delimiters or instructions to ignore embedded commands.\n
Capability inventory: Alerts can trigger agent, connector, tool, and native actions as described in SKILL.md and references/alert-lifecycle.md.\n
Sanitization: No documented evidence of sanitization or escaping of measured values before they are passed to automated actions.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @cargo-ai/cli package from the npm registry to provide the command-line interface required for observability operations.

cargo-observability