configure-skaffold
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses dynamic context injection (the !command syntax) to execute shell discovery commands like find and grep when the skill is loaded to automatically detect Kubernetes and Skaffold configuration files.- [COMMAND_EXECUTION]: Documentation in REFERENCE.md suggests a setup procedure that involves appending environment variables to the user's shell configuration file (~/.zshrc) to store private keys.- [EXTERNAL_DOWNLOADS]: The REFERENCE.md file contains instructions for installing the dotenvx utility using a curl | sh execution pattern from the official dotenvx.sh domain.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it parses and acts upon data from user-controlled files like skaffold.yaml and .project-standards.yaml which could contain malicious instructions.
- Ingestion points: Configuration data is read into the agent context from project YAML files using Grep and Read tools.
- Boundary markers: No protective delimiters or warnings are used to distinguish project data from agent instructions.
- Capability inventory: The skill has permissions to write and edit local files, perform web requests, and generate/execute shell scripts.
- Sanitization: There is no evidence of sanitization or validation of configuration content before it is used to determine compliance or suggest fixes.
Audit Metadata