helm-generation
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various helm CLI commands, such as 'helm show', 'helm lint', and 'helm install', using placeholders like '', '', and ''. This creates a surface for command injection if the agent blindly uses user-supplied strings in a shell environment.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection (Category 8) as it processes untrusted external data (such as Docker Compose files or Helm chart metadata) and possesses shell execution capabilities. ● Ingestion points: User-provided chart names, versions, and Docker Compose content (SKILL.md). ● Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded commands in the processed data. ● Capability inventory: Shell execution of 'helm' CLI tools across multiple steps (SKILL.md). ● Sanitization: Absent; the instructions do not include steps for validating or escaping inputs before incorporating them into shell commands.
Audit Metadata