tanstack-query-svelte-debugging
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data during its primary debugging workflow.
- Ingestion points: Step 2 of the process in SKILL.md directs the agent to gather evidence from 'code, logs, traces, metrics, generated output, database plans, config, or failing tests,' all of which are externally controlled sources.
- Boundary markers: The instructions do not specify the use of delimiters or specific instructions to ignore embedded commands when the agent processes this content.
- Capability inventory: The skill utilizes file system search capabilities and general agent reading tools to process the gathered evidence.
- Sanitization: There is no explicit requirement for the agent to sanitize, escape, or validate the content of the logs or code snippets before analysis.
Audit Metadata