crd-impact
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to run commands like git diff, find, and grep. It incorporates user-supplied input from $ARGUMENTS directly into these command lines, which creates a potential surface for command injection if the input is not properly sanitized.
- [PROMPT_INJECTION]: The skill reads and processes the content of CRD definition files and source code from the repository to perform its analysis. This makes it vulnerable to indirect prompt injection where instructions embedded in those files (e.g., in comments or field descriptions) could attempt to influence the agent's behavior.
- Ingestion points: $ARGUMENTS and repository files (CRD definitions, Go source code, YAML manifests).
- Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded content when reading files.
- Capability inventory: Bash, Read, Grep, Glob.
- Sanitization: Absent; the instructions do not prescribe any validation or escaping for input or file content.
Audit Metadata