gh-repo-bootstrap
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's core functionality relies on executing shell commands through
gitand the GitHub CLI (gh). While these are standard development tools, the agent is granted the capability to perform actions like repository creation, authentication setup, and code pushing within the host environment. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and stage local project files (
git add .) for the initial commit. This presents a surface for indirect prompt injection where malicious instructions embedded in code comments or project documentation could attempt to influence the agent's behavior during the execution of the workflow. - [DATA_EXPOSURE]: Although the skill handles GitHub authentication tokens, it includes specific guardrails to prevent the exfiltration of credentials. It explicitly instructs the agent to avoid pushing
.envfiles, secrets, or local credential files to the remote repository, adhering to standard secret management practices.
Audit Metadata