quack
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a controlled routing mechanism using local static configuration files. It does not perform network operations, access sensitive credentials, or execute arbitrary shell commands. All routing is based on a predefined set of aliases.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied intent strings to route to specific capabilities. 1. Ingestion points: The intent parameter provided by the user in the quack command. 2. Boundary markers: Explicit quack activation requirement and normalization of the intent string. Instructions for sub-tasks are retrieved from a local runbook. 3. Capability inventory: Dispatches tasks to internal skills like duck-patch or duck-debug via the task tool. 4. Sanitization: Normalizes the intent by stripping punctuation and whitespace.
Audit Metadata