writing-codeceptjs-tests
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from live web applications (such as ARIA snapshots and HTML content) to generate test code, creating a surface for potential indirect prompt injection attacks.\n
- Ingestion points: Untrusted web content is retrieved through the
run_codeandrun_testMCP tools defined in the workflow.\n - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the retrieved browser data.\n
- Capability inventory: The agent has the ability to execute JavaScript in a browser session via
run_codeand write new test files to the local filesystem.\n - Sanitization: No explicit sanitization or validation logic is specified for the data retrieved from external web pages before it is processed by the agent.\n- [DYNAMIC_EXECUTION]: The skill facilitates the generation and runtime execution of JavaScript code to drive browser interactions.\n
- The
run_codetool is used to executeI.*actor commands dynamically against a live page.\n - Test scenarios are scaffolded, executed via the
run_testMCP tool, and then modified at runtime based on the session outcome.\n - While powerful, these execution patterns are the primary intended function of the skill for test authoring and exploration.
Audit Metadata