code-search
Warn
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses 'bun x codebasesearch', which downloads and executes a package from the NPM registry at runtime. The package is not provided by a trusted organization or the specific skill author's documented vendor namespace.- [COMMAND_EXECUTION]: The skill utilizes the 'Bash' tool to run shell commands for searching the codebase.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection where malicious instructions embedded in the codebase could be processed by the agent. * Ingestion points: Results from 'codebasesearch' (SKILL.md). * Boundary markers: Absent; there are no delimiters or instructions to ignore instructions found within search results. * Capability inventory: The skill allows shell command execution via 'Bash' (SKILL.md). * Sanitization: No filtering or escaping is applied to the output of the search tool before it is returned to the agent context.
Audit Metadata