windsurf-security-basics
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow for analyzing repository content, which presents a surface for indirect prompt injection if the analyzed repository contains malicious instructions.
- Ingestion points: The skill uses the
ReadandGreptools to inspect repository files, configuration settings, and logs inSKILL.md(Steps 1 and 2). - Boundary markers: The instructions explicitly mandate the creation of
.codeiumignoreand.gitignorefiles to exclude sensitive data and untrusted paths from the AI's context. - Capability inventory: The skill utilizes
ReadandGrepfor auditing andWritefor generating security review reports as defined in theallowed-toolsmetadata and Output section. - Sanitization: The skill includes strict instructions to never write literal credentials and to use human-approved secret management (Step 4 and Step 5).
Audit Metadata