infra-nomad-deployment
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data such as application logs, Nomad job specifications, and infrastructure metrics. This creates a surface for indirect prompt injection if the processed data contains malicious instructions targeting the agent.
- Ingestion points: SKILL.md (Process step 4 and Evidence section).
- Boundary markers: Absent; no specific delimiters are defined to separate ingested data from agent instructions.
- Capability inventory: The skill facilitates the use of infrastructure management tools including Nomad, Vault, and Consul as described in the reference files.
- Sanitization: Absent; the instructions do not specify any validation or sanitization of the external content before processing.
Audit Metadata