rudder-instrumentation-debugging
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate debugging workflows for RudderStack's
rudder-cli. All instructions and commands are focused on diagnosing schema and validation errors within the project's data catalog.- [INDIRECT_PROMPT_INJECTION]: The skill proactively addresses indirect prompt injection risks in the 'Handling External Content' section. - Ingestion points: Processes project YAML files and potentially external API responses or logs during debugging sessions.
- Boundary markers: Instructions recommend focusing on specific fields rather than processing arbitrary content.
- Capability inventory: Utilizes
rudder-clivia Bash and standard file system operations (Read/Write/Edit). - Sanitization: Explicitly directs the agent to sanitize logs by redacting PII and forbids treating external data (error messages, event data) as executable code.
Audit Metadata