windsurf-code-completion
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages project-level configuration files which serves as an ingestion surface for potentially untrusted data.
- Ingestion points: Reads from
.windsurf/completion/preferences.json,language-config/*.json,snippets/custom-snippets.json, and.windsurfrulesin the project root. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions within these data files.
- Capability inventory: The skill is authorized to use
Read,Write, andEdittools to manipulate these files. - Sanitization: There is no evidence of content validation or sanitization when reading from or writing to these configuration templates.
Audit Metadata