playwright-documentation-root-cause

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it is designed to ingest and process untrusted data from external test outputs and logs.\n
  • Ingestion points: The skill reads failing test output, trace artifacts, HTML reports, and application logs (defined in SKILL.md).\n
  • Boundary markers: None identified. There are no explicit instructions to the agent to ignore or delimit embedded instructions within the ingested logs.\n
  • Capability inventory: The skill does not request or use capabilities for file system writes (metadata explicitly sets dispatcher-writes-files to false) or network operations.\n
  • Sanitization: No sanitization or validation of the ingested test artifacts is documented in the analysis workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 08:14 AM
Security Audit — agent-trust-hub — playwright-documentation-root-cause