datadog-hardened
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a Python script (
datadog.py) to interact with the Datadog REST API. All management tasks are routed through this script using standard CLI patterns. - [PROMPT_INJECTION]: The skill maintains an attack surface for indirect prompt injection due to the nature of its operational data ingestion and write capabilities.
- Ingestion points: The agent processes external, untrusted data including Datadog logs, event descriptions, monitor queries, and incident details retrieved from the Datadog API.
- Boundary markers: The provided instructions in
SKILL.mddo not implement explicit delimiters or instruction-isolation markers to distinguish between the agent's core logic and the data retrieved from external sources. - Capability inventory: The skill allows the agent to perform sensitive actions such as deleting monitors (
monitor-delete), deleting dashboards (dashboard-delete), muting alerts (monitor-mute), and creating new events or monitors. - Sanitization: No evidence of sanitization, escaping, or schema validation for the data ingested from the Datadog API is present in the skill's instructions or metadata.
Audit Metadata