Playwright Test Report to Slack
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from Playwright test reports (HTML and JSON) to generate Slack messages. This creates a surface for indirect prompt injection where malicious test output could attempt to override agent behavior or inject content into Slack channels.
- Ingestion points: Test reports located in the
playwright-reportdirectory. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are described.
- Capability inventory: Reading local files and performing network operations via the Slack Web API.
- Sanitization: No evidence of validation or sanitization of the test failure messages or suite names before processing.
- [DATA_EXFILTRATION]: The skill transmits test results and screenshots to Slack via the Web API (chat.postMessage, files.uploadV2). This involves accessing local report files and potentially environment variables for Slack bot tokens. Slack is recognized as a well-known communication service.
- [PROMPT_INJECTION]: The YAML frontmatter includes a
verification: security_reviewedfield. This is a self-claimed status and does not constitute an objective security assessment.
Audit Metadata