deepgram-incident-runbook
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources such as the Deepgram Status API and transcription responses to assess service health. This is standard operational behavior for an incident response tool.
- Ingestion points: Deepgram API responses, status JSON, and Kubernetes logs (SKILL.md, references/implementation.md).
- Boundary markers: No specific boundary markers are used in the automated scripts.
- Capability inventory: The skill uses Bash for curl and kubectl for triage operations as defined in the frontmatter.
- Sanitization: The scripts utilize jq to parse JSON data, providing structured access to external content.
- [DATA_EXPOSURE]: The skill follows secure practices by using environment variables ($DEEPGRAM_API_KEY) for authentication rather than hardcoded credentials.
Audit Metadata