T09 · Insecure Skill Coding Practices
- Location
scripts/deepwiki.js:76- Finding
Untrusted Repository Documentation Is Embedded in a System Prompt
- Content
View full analysis
- Remediation
View remediation
\n${docText}\n\n\n` + `Question: ${extra}` } ] ``` This separation does not eliminate all model-level prompt-injection risk, but it creates a clearer trust boundary and materially reduces the likelihood that repository text will be treated as authoritative application policy. ]]>
