eval-code-quality
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill intentionally executes build and type-checking commands including
npm run buildandnpx tsc --noEmit. These are standard tools used to verify the functional integrity of a codebase. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted project data that influences its execution.
- Ingestion points: The skill reads
spec.md,plan.md,tsconfig.json,package.json, and changed files (git diffs) from the project being evaluated. - Boundary markers: There are no explicit instructions or delimiters used to ensure the agent treats the content of these files strictly as data rather than instructions.
- Capability inventory: The skill has the capability to execute shell commands (
npm,npx) based on the configuration found in the ingested files. - Sanitization: No validation or sanitization of the scripts defined in
package.jsonor configurations intsconfig.jsonis performed prior to execution.
Audit Metadata