debug-cucumber-html-report
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow where the agent interacts with external HTML report files. Because these files are untrusted external data, they could contain instructions designed to manipulate the agent's behavior during inspection (Indirect Prompt Injection).
- Ingestion points: Local HTML report files specified in the documentation.
- Boundary markers: No delimiters or ignore-instructions warnings are provided to separate the report content from the agent's system prompt.
- Capability inventory: The skill uses playwright-cli, which includes capabilities like open, snapshot, eval, click, and goto.
- Sanitization: The instructions do not include steps for sanitizing or validating the content of the HTML reports before the agent processes them.
- [COMMAND_EXECUTION]: The skill requires setting the PLAYWRIGHT_MCP_ALLOW_UNRESTRICTED_FILE_ACCESS environment variable. This configuration instructs the underlying tool to bypass standard file access restrictions, granting it the ability to read any file on the local system to support its debugging functions.
Audit Metadata