rudder-instrumentation-planning
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'rudder-cli' command-line tool to validate and apply instrumentation plans to the workspace. This is a standard vendor-provided utility for the skill's primary purpose.
- [CREDENTIALS_SAFE]: The documentation explicitly provides best-practice guidance for security, advising users to never track sensitive data like passwords or tokens, to hash PII, and to use environment variables for workspace tokens while ensuring '.env' files are added to '.gitignore'.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow that ingests business requirements and user journey descriptions to generate YAML configurations. This represents a potential surface where untrusted data could influence agent-generated output.
- Ingestion points: Business goals and user journey definitions processed in Phase 1 (Discovery) of
SKILL.md. - Boundary markers: None identified.
- Capability inventory: Uses 'Bash(rudder-cli *)', 'Read', 'Write', and 'Edit' tools to generate and apply configurations.
- Sanitization: None identified.
Audit Metadata