c4-level2-container
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions create an attack surface for indirect prompt injection by directing the agent to ingest and analyze various untrusted external data sources from the project environment.
- Ingestion points: The workflow in
SKILL.mdrequires the agent to inspect build artifacts, deployment descriptors, infrastructure configurations, database/message schemas, API clients, network policies, and runtime traces. - Boundary markers: The instructions do not include specific delimiters or directions for the agent to ignore instructions that might be embedded within these external files.
- Capability inventory: The skill involves extensive file system read access to perform the architectural analysis, which could be exploited if malicious content is present in the analyzed files.
- Sanitization: No sanitization or validation rules are defined for the content extracted from the external evidence sources.
Audit Metadata