find-untested-sources
Warn
Audited by Snyk on Jul 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). Yes: the required workflow ingests outsider-authored free text by reading and parsing the repository’s source/test files from the caller-specified
<repo-root>(e.g.,File.ReadAllText(file)on arbitrary.csfiles, thenCSharpSyntaxTree.ParseText(text)), and the resulting extracted identifiers/usings are included in the JSON that becomes LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata