nvcf-self-managed-installation
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided infrastructure configuration files, including Helmfile stacks, environment YAMLs, and secrets files, and executes system commands based on their content. This creates a surface where malicious instructions embedded in these files could be executed by the agent.
- Ingestion points: The skill reads files from the user-provided
nvcf-self-managed-stackdirectory, specificallyenvironments/*.yamlandsecrets/*.yaml. - Boundary markers: There are no specific delimiters or instructions to ignore embedded prompts within the ingested files.
- Capability inventory: The skill uses the
Shelltool to execute high-privilege administrative commands such askubectl,helmfile,make,docker, andhelm. - Sanitization: No sanitization, escaping, or schema validation is performed on the content of the configuration files before they are used to influence shell command execution.
Audit Metadata