running-webdriverio-tests
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of test commands including
npx wdioand project-defined scripts vianpm run. These are standard operations for a testing skill. - [INDIRECT_PROMPT_INJECTION]: The skill is instructed to ingest data from external project files to influence its behavior, creating a potential injection surface.
- Ingestion points: The skill reads
.webdriverio-skills/project-context.md,.webdriverio-skills/project-context.json,.webdriverio-skills/custom-rules.md, andreferences/website-analysis/<target>/website-analysis.mdto prioritize test runs and select scripts. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within these files are specified.
- Capability inventory: The skill has the ability to execute shell commands (
npx,npm) and read various files within the repository. - Sanitization: There is no mention of sanitizing or validating the content of the project context or analysis files before using them to determine execution parameters.
Audit Metadata