llm-prices
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a bash tool to run the model-prices command and jq to parse the resulting JSON data.
- [EXTERNAL_DOWNLOADS]: The instructions refer to the author's official MCP server (mcp.hedwigai.com) and a plugin hosted on their GitHub (un-seen/hedwigai-skills).
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the model-prices command. * Ingestion points: Command output from model-prices (JSON). * Boundary markers: None explicitly mentioned. * Capability inventory: Access to the bash tool for command execution and file operations in /tmp. * Sanitization: Relies on jq for structural parsing of JSON output.
Audit Metadata