e2e-testing-automation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing application source code and interacting with web interfaces to generate or execute automated tests. This workflow creates a potential surface for indirect prompt injection, where an attacker could embed malicious instructions in comments, metadata, or UI elements of the application being tested to influence the agent's actions.\n
- Ingestion points: The agent processes source code files (e.g., via
scripts/scaffold-tests.sh) and application UIs (referenced in Cypress/Playwright guides) to derive test logic.\n - Boundary markers: No specific delimiters or instructions to ignore embedded prompts in analyzed content are provided in the instructions.\n
- Capability inventory: The skill facilitates file system interaction (reading source, writing tests) and network interaction (browser automation), which could be misused if the agent obeys instructions hidden in the processed data.\n
- Sanitization: The reference implementations do not include explicit sanitization or filtering of content extracted from untrusted application files or web pages.
Audit Metadata