cofounder-repo-setup

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands and a bundled bash script (scripts/repo-init.sh) to manage Git repositories and GitHub authentication. Commands include gh auth, git init, and repository creation via the GitHub CLI.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data (repository name and visibility) which is then interpolated into a shell execution string.
  • Ingestion points: User input for the repository name and visibility level as described in SKILL.md.
  • Boundary markers: No explicit boundary markers or sanitization instructions are provided to the agent for handling these inputs.
  • Capability inventory: The skill has the capability to execute arbitrary bash commands and interact with the file system and network via git and gh.
  • Sanitization: While the bundled script scripts/repo-init.sh uses shell quoting for variables, the initial command construction by the agent (e.g., bash ... <repo-name>) remains a potential surface for command injection if the repository name contains shell metacharacters.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 06:23 PM
Security Audit — agent-trust-hub — cofounder-repo-setup