qa-codeceptjs-writer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface by processing data from potentially untrusted external sources to generate executable test code.
- Ingestion points: Workflow Step 1 in
SKILL.mdidentifies that the skill reads test case data from sources includingqa-testcase-from-docs,qa-manual-test-designer, andqa-browser-data-collector. - Boundary markers: The instructions do not define delimiters or specific 'ignore' directives to prevent the agent from following malicious instructions embedded within the ingested test cases.
- Capability inventory: The skill is configured to write generated test files and scenarios to the project's local filesystem (
tests/e2e). - Sanitization: There is no evidence of validation, escaping, or filtering of the external input before it is interpolated into the code generation prompts.
Audit Metadata