helm-chart-builder
Warn
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: MEDIUMCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: Example configuration files contain hardcoded credentials used to demonstrate auditing capabilities.
examples/values.yaml: Hardcoded database connection stringpostgres://admin:pr0duction_s3cret@postgres:5432/acme.examples/values.yaml: Hardcoded API keysk-live-abc123def456ghi789.examples/values.yaml: Hardcoded database passwordsupersecret123.examples/values.yaml: Hardcoded Redis URLredis://:redis_pass@redis:6379.- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted Helm charts and values files, creating a potential vector for indirect prompt injection.
- Ingestion points:
scripts/chart_analyzer.pyandscripts/values_validator.pyread and process local YAML and template files. - Boundary markers: The skill does not use specific delimiters or instructions to prevent the agent from following directions embedded in the files being analyzed.
- Capability inventory: The tools are limited to reading local files and performing static analysis; no file-write or network capabilities are present.
- Sanitization: Input data is parsed using custom logic but is not sanitized to remove potential instructions targeting the AI agent.
Audit Metadata