skills/jeremylongshore/claude-code-plugins-plus-skills/guidewire-core-workflow-b/Gen Agent Trust Hub
guidewire-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill metadata in
SKILL.mdrequests access toBash(curl:*)andBash(npm:*)tools, which allows the agent to execute shell commands for network operations and package management. This is consistent with the skill's enterprise integration purpose. - [EXTERNAL_DOWNLOADS]: The skill references documentation from
docs.guidewire.cominSKILL.md. Guidewire is a well-known technology service, and these references are documented neutrally. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection. 1. Ingestion points: Functions like
createFNOL,addExposure, andcreatePaymentinSKILL.mdingest untrusted data from external sources. 2. Boundary markers: The provided code snippets lack delimiters or 'ignore embedded instruction' warnings to isolate user data from the logic. 3. Capability inventory: The skill has access to file system modification (Write,Edit) and shell execution (Bash). 4. Sanitization: No input validation or escaping routines are implemented in the logic provided.
Audit Metadata