Security audit
Security checks for vulnerabilities and agentic risk
The GPTZero workflow is coherent, but its CLI dependency can automatically install other agent skills without clear notice in this skill.
Review the CLI's broader skill installation behavior before allowing setup. Its documented OO_SKILLS_SYNC_DISABLED=1 setting disables startup synchronization; installer behavior needs separate review. Prefer a verified, pinned installation and submit only text you are authorized to share with OOMOL and GPTZero. The exact remote installers remain unverified; no malicious payload was established.
The supplied command performs remote software installation, not GPTZero searching or reading. Nothing in the provided chunk establishes that installing the Oomol CLI is a necessary supporting step for GPTZero access, and remote script execution is not disclosed in the declared purpose. The downloaded script's further behavior cannot be determined from this chunk.
The supplied code contains only a login command, with no GPTZero-specific resource selection, search, or read operation. Authentication could support a GPTZero integration, but no such integration is present in this chunk; its entire observable purpose is login rather than the declared data-access functionality.
The setup command executes a mutable remote script directly in Bash without verifying its contents, signature, or a pinned digest; the PowerShell alternative follows the same pattern. Compromise of the distribution endpoint or release process could therefore execute arbitrary code with the invoking user's privileges, although the missing-CLI condition limits when this path is reached.
oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):
curl -fsSL https://cli.oomol.com/install.sh | bash # macOS / Linux
The workflow instructs the agent to execute connector actions, and its sole action analyzes document text using GPTZero. Calling all untagged actions reads that are safe to run directly overlooks the disclosure of potentially sensitive document content to a third-party service; the skill never explicitly warns users about this transmission.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.
- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.
## Resources