writing-tests
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes existing project source code and configuration files to determine the appropriate test setup and generate new tests. This introduces a potential surface for indirect prompt injection if the source code being analyzed contains malicious instructions designed to manipulate the agent's behavior.
- Ingestion points: Reads
package.json, source files (e.g.,.ts,.tsx), and existing test configurations as described inSKILL.mdsteps 1 and 3. - Boundary markers: The instructions do not include specific delimiters or warnings to the agent to ignore instructions embedded within the code content it processes.
- Capability inventory: The skill executes shell commands (
npm install,npm test,npx jest) and writes new files to the filesystem. - Sanitization: There is no explicit sanitization or validation of the code content before it is processed for test generation.
Audit Metadata