scan-integration-tests
Warn
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill identifies and reads sensitive configuration files as part of its scanning process.\n
- Evidence: Phase 1 and Phase 2 instructions specifically target files such as
.env.test,appsettings.test.json, and test container configurations to extract test setup patterns.\n - Risk: These files are commonly used to store environment variables, database connection strings, and API keys for test environments, exposing them to the agent's context during the scan.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from the project's codebase.\n
- Ingestion points: The skill scans the entire test suite, including project manifest files (
package.json,*.csproj,pom.xml), configuration files (pytest.ini,conftest.py), and all test source code.\n - Boundary markers: There are no explicit instructions or delimiters used to isolate untrusted data from the agent's internal instructions.\n
- Capability inventory: The agent has the capability to read any file in the project and write to both
plans/reports/anddocs/project-reference/.\n - Sanitization: No input validation or sanitization is performed on the data retrieved from the codebase before it is used to generate reports and documentation.
Audit Metadata