glean-performance-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external document content for indexing via the Glean API (
SKILL.md). While inherent to its primary purpose, processing untrusted external data presents a surface for indirect prompt injection where malicious instructions could be embedded in document metadata or body content. - Ingestion points: Processes a
docsarray of objects containing document content and metadata in theindexDocsBatchedfunction. - Boundary markers: None specified in the instructional code snippets to separate document content from processing logic.
- Capability inventory: Utilizes tools for reading, writing, and editing files, along with network access for Glean API operations.
- Sanitization: The provided examples focus on performance logic (batching/concurrency) rather than content sanitization, which is expected for the skill's scope.
Audit Metadata