Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed worktree cleanup tool with strong user-confirmation and safety checks around deletion.
Install only if you want an agent to audit and clean local Git worktrees. Review the proposed exact paths carefully, keep branches unless you intentionally choose deletion, and do not approve cleanup for worktrees with unknown sensitive ignored files or uncertain issue/task state.
Referenced artifact was not completely inspected
his file from the skill directory. Before invoking the bundled script, resolve `scripts/worktree_cleanup.py` to an absolute path so the command does not depend
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
"vendor",
}
SENSITIVE_IGNORED_GLOBS = (
".env",
".env.*",
"*.db",
"*.db3",
Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.
check: bool = True,
cwd: Optional[Path] = None,
) -> subprocess.CompletedProcess[str]:
env = os.environ.copy()
env.setdefault("LC_ALL", "C")
result = subprocess.run(
list(command),
The skill invokes shell commands, reads reference files, and writes temporary artifacts, but it does not declare a restrictive tool scope such as permissions or allowed-tools. In an agent environment, this can lead to over-broad tool access and increases the blast radius if the skill is misused, modified, or combined with prompt injection from untrusted issue content or repository data.
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
) -> subprocess.CompletedProcess[str]:
env = os.environ.copy()
env.setdefault("LC_ALL", "C")
result = subprocess.run(
list(command),
cwd=str(cwd) if cwd else None,
env=env,
No suspicious patterns detected.