infra-production-readiness-review
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is inherently designed to process untrusted external data, including job specifications, Dockerfiles, and deployment manifests, which creates a vulnerability surface for indirect prompt injection attacks.
- Ingestion Points: As described in
SKILL.md, the agent is instructed to map request paths and review job specs, Dockerfiles, proxy configurations, deployment manifests, logs, and metrics. - Boundary Markers: The instructions do not define clear delimiters or boundary markers to separate the untrusted data being reviewed from the agent's core instructions.
- Capability Inventory: The skill asks the agent to collect evidence from configuration files, container states, and logs, which involves reading various files and potentially executing diagnostic tools.
- Sanitization: There are no instructions for sanitizing or validating the contents of the external files before they are processed by the agent.
Audit Metadata