ljg-structure
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of shell commands (
date) to generate timestamps for file naming and organization. - [COMMAND_EXECUTION]: The skill instructs the agent to write generated content to the local filesystem at a specific path (
~/Context/). - [INDIRECT_PROMPT_INJECTION]: Ingestion points: The workflow ingests untrusted information from the user to perform structural analysis in Workflows/FindStructure.md. Boundary markers: No specific boundary markers or instructions are provided to the agent to ignore potentially malicious instructions embedded in the user input. Capability inventory: The agent has permissions to execute shell commands and write to the local filesystem across its operational scripts. Sanitization: The subject variable (
{主题}), sourced directly from user input, is interpolated into a file path in SKILL.md without validation or sanitization, creating a potential surface for path manipulation.
Audit Metadata