exploration
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard system commands such as ls, find, grep, tree, and cat to perform directory traversal and file content analysis. These operations are localized to the provided directory and are used for reconnaissance and mapping.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads untrusted data from the local codebase (via cat and grep in SKILL.md) and provides it to the agent. Ingestion points: local file reads during codebase reconnaissance. Boundary markers: absent. Capability inventory: read-only shell commands (ls, find, grep, cat, tree, wc). Sanitization: absent. This surface is considered low risk given the skill's primary purpose as a discovery tool.
Audit Metadata