helm-chart-builder
Warn
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow instructs the agent to execute external scripts such as 'scripts/chart_analyzer.py' and 'scripts/values_validator.py' along with CLI tools like 'helm lint'. These scripts are referenced but not provided within the skill source files.
- [EXTERNAL_DOWNLOADS]: The documentation references installation from a third-party GitHub repository ('github.com/alirezarezvani/claude-skills') and a third-party installer ('clawhub'), which are not affiliated with the author 'Roger-235'.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing untrusted Helm chart data to generate security and quality reports. Maliciously crafted charts could influence the agent's output or trigger unintended behaviors. Ingestion points: Chart metadata, template logic, and values files. Boundary markers: No delimiters are specified to isolate user data from agent instructions. Capability inventory: The agent has shell execution and file read/write permissions. Sanitization: No validation steps are defined for the content of analyzed charts.
- [DATA_EXFILTRATION]: The skill processes 'values.yaml' and 'secret.yaml' files. While best practices are encouraged, the workflow inherently accesses potentially sensitive configuration data, creating a surface for accidental exposure or data extraction during the analysis process.
Audit Metadata