robot-framework-skill
Fail
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONSAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates an automated testing environment that processes external data from test scripts and network responses, representing a surface for indirect prompt injection.\n
- Ingestion points: Untrusted data enters the context through CSV data files used for parameterization (e.g.,
data/login_tests.csv) and through network responses during API testing (viaRequestsLibrary) or page content during UI testing (viaSeleniumLibrary).\n - Boundary markers: The templates do not utilize specific delimiters or instructions to ignore commands embedded within the processed data.\n
- Capability inventory: The skill allows for the execution of custom Python logic (
CustomLibrary.py), network operations, and file system interactions for logging results.\n - Sanitization: The provided code examples do not demonstrate validation or sanitization of external input strings before they are utilized as keyword arguments.\n- [SAFE]: The skill manages remote browser authentication using environment variables (
LT_USERNAME,LT_ACCESS_KEY), which is the recommended method for handling sensitive credentials in CI/CD environments. The use of the official LambdaTest hub endpoint is a legitimate vendor resource consistent with the skill's primary purpose.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata