analyze-code-structure
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard shell commands (
find,tree,grep) to list project files and search for code patterns like classes and functions. These operations are intended for read-only exploration of the local directory structure. - [EXTERNAL_DOWNLOADS]: The skill provides an installation command that downloads the instruction file from a public GitHub repository. This is a standard mechanism for skill deployment and uses a well-known, trusted platform.
- [PROMPT_INJECTION]: The skill performs text searching on local source files, which creates a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: File contents read via
grepand file paths listed viafindandtreeinSKILL.md. - Boundary markers: No explicit markers or warnings are used to tell the agent to disregard instructions found within the code files.
- Capability inventory: The skill is restricted to read-only filesystem inspection and search operations.
- Sanitization: No sanitization or filtering of the file content is performed prior to the agent processing the search results.
Audit Metadata