logs-datadog
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of documentation and reference files (Markdown). No executable scripts, malicious instructions, or obfuscated content were detected.
- [CREDENTIALS_UNSAFE]: The skill identifies the need for project tokens but correctly instructs the user to manage them via environment variables and explicitly warns against the use of high-privilege personal tokens.
- [DATA_EXFILTRATION]: All network operations described involve sending diagnostic logs to the vendor's official endpoint (us.i.posthog.com), which is consistent with the skill's primary purpose.
- [PROMPT_INJECTION]: While the skill describes an integration with a Model Context Protocol (MCP) server that allows an agent to query logs (a potential ingestion point for untrusted data), it does not contain any instructions that attempt to bypass AI safety filters or override agent behavior.
Audit Metadata