code-search
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: Provides templates and examples for executing shell-based search commands such as
grepandripgrepfor codebase analysis.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it performs deep analysis on external, untrusted source files.\n - Ingestion points: File content is ingested for pattern matching and dependency analysis via
readFileandextractImportsas described inSKILL.md.\n - Boundary markers: The skill does not provide instructions to the agent to use delimiters or ignore natural language commands embedded in the files being scanned.\n
- Capability inventory: The skill leverages the agent's ability to read files, traverse directories, and execute shell commands.\n
- Sanitization: No sanitization or instruction filtering is applied to the content extracted from project files before it is processed by the agent.
Audit Metadata