github-search
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using the GitHub CLI (gh) to search repositories, code, and issues.
- [DYNAMIC_EXECUTION]: The skill uses subshells and command interpolation to construct API search calls at runtime using template strings.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from GitHub (repository names, descriptions, and code contents) which is considered untrusted external input.
- Ingestion points: Search results from gh search and gh api calls (SKILL.md).
- Boundary markers: Absent. The instructions do not explicitly mandate the use of delimiters for content returned from GitHub.
- Capability inventory: The skill uses the Bash tool to execute gh commands and jq for processing.
- Sanitization: The skill demonstrates the use of jq -sRr @uri to URL-encode queries, which provides a layer of protection against command injection in the query string.
Audit Metadata