superplane-cli
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's architecture for handling external data creates a potential indirect prompt injection surface.
- Ingestion points: The skill reads and processes external YAML files (such as
canvas.yamlandconsole.yaml) and captures data from thesuperplaneCLI's output during runtime. - Boundary markers: There are no specific delimiters or instructions to the agent to disregard instructions that might be embedded in the YAML files or the command-line outputs.
- Capability inventory: The skill utilizes the
superplaneCLI, which has capabilities including network access, secret management, and application modification. It also performs file system operations to manage configuration files. - Sanitization: No validation or sanitization routines are specified for checking the content of the YAML files or CLI outputs before they are processed by the agent.
Audit Metadata