edgeone skill scanner
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill identifies and reads files from local application directories (e.g., ~/.codebuddy/plugins/, ~/.cursor/extensions/) to conduct security audits. This file system access is strictly scoped to the skill's primary function as a scanner and originates from a trusted vendor.
- [COMMAND_EXECUTION]: Static analysis involves using shell-based tools to retrieve and inspect the contents of skill files to detect vulnerabilities.
- [PROMPT_INJECTION]: As the skill ingests and processes untrusted data from third-party skill files, it is subject to indirect prompt injection risks. However, the instructions explicitly guide the agent to detect and flag such patterns in audited content.
Audit Metadata