code-refactoring-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides educational content and instructions for refactoring code using common TypeScript patterns and standard developer tools such as
gitandnpm. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads and processes external source code files.
- Ingestion points: The skill reads local source code files in
SKILL.md(Step 1) using thecatcommand. - Boundary markers: Absent; there are no explicit delimiters or instructions to ignore potential instructions embedded in the files being processed.
- Capability inventory: The workflow described in
SKILL.mdinvolves executing shell commands includingnpm test,npx tsc, andgit commit. - Sanitization: Absent; the skill does not perform sanitization of file content before the agent analyzes it for refactoring.
Audit Metadata