playwright-test-results
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- Command Execution: The skill utilizes shell commands like
nodeand the GitHub CLI (gh) to synchronize test artifacts and perform database updates. These operations are necessary for the skill's primary function of maintaining a local cache of CI results. - Credential Access: The instructions include the use of
gh auth tokento provide a temporary authentication token to the database update script. This is a standard practice for local development environments to interact with GitHub APIs securely without hardcoding secrets. - Data Ingestion Surface: The skill processes data from external CI runs, including test titles and error messages. As this data originates from the repository's CI environment, it represents a surface where the agent processes external content. The skill uses structured SQL queries to manage this data safely.
- Dynamic Script Execution: The documentation provides examples of executing inline JavaScript via
node -eand heredocs to handle data from DuckDB. This pattern is common in utility-focused skills for processing and formatting structured data for the user.
Audit Metadata