auth-session-audit
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a structured testing methodology for observing session lifecycles in a web application context. All described checks are standard quality assurance and security verification procedures.
- [COMMAND_EXECUTION]: The skill uses Playwright browser automation to perform its tasks. These operations are focused on session state manipulation (clearing cookies or tokens) and navigating to specific application states to verify functional correctness.
- [PROMPT_INJECTION]: The auditing process involves interacting with external web content, which constitutes a surface for indirect prompt injection.
- Ingestion points: The skill observes and processes content from the target application's web pages and session storage in SKILL.md.
- Boundary markers: No explicit delimiters or boundary instructions are defined in the skill text.
- Capability inventory: The agent utilizes network access via Playwright browser contexts to interact with the user-provided target URL.
- Sanitization: No specific input sanitization is described, as the skill's primary function is to report observed browser behavior into a markdown table.
Audit Metadata