code-research

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads repository data from GitHub using the gh CLI tool. This is a well-known service used for its intended purpose of source code management.
  • [COMMAND_EXECUTION]: The skill executes the gh repo clone command to transfer remote repositories to the user's local ~/code directory. The command is constructed based on repository identifiers extracted from user input.
  • [PROMPT_INJECTION]: There is an inherent surface for indirect prompt injection because the skill is designed to ingest and analyze untrusted content from external repositories. A sub-agent is tasked with researching this code, which could contain malicious instructions or documentation designed to influence the agent's research findings or behavior. The skill lacks explicit boundary markers or instructions to treat repository content as untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 08:43 AM