Security audit
Security checks for vulnerabilities and agentic risk
Review is warranted because setup runs unverified remote code, and the required CLI documents persistent changes to agent skills that this skill does not explain.
Review and install a verified CLI release yourself before enabling this skill. Disable startup skill synchronization with OO_SKILLS_SYNC_DISABLED=1 if you do not want additional agent skills installed or refreshed. Send only documents you authorize OOMOL and OCR Web Service to process, and consider page-credit costs. The complete bundled artifact was inspected, but remote installer contents and hosted connector protections remain unverified.
The supplied command contains no OCR Web Service interaction. It instead executes a remote installer from an unrelated domain, with no demonstrated connection to the declared OCR functionality. The downloaded script's contents and resulting system changes cannot be determined from this chunk.
Piping the installer URL directly into bash executes whatever the endpoint currently serves, without a pinned version or independent integrity verification. HTTPS protects transport but not a compromised publisher or distribution service, creating a potential route to local code execution and access to agent-readable files or credentials; this is the same underlying issue as SQP-2.
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 processing action downloads a document and uploads it to an external OCR provider, yet the blanket rule treats untagged actions as reads that are safe to run directly. This can obscure external disclosure and quota consumption; the explicit public-URL requirement and an ordinary user request for OCR reduce the risk, but do not make processing side-effect-free.
The setup instructions pipe remotely retrieved shell and PowerShell scripts directly into interpreters without establishing a reviewed or pinned artifact. If the distribution endpoint or release pipeline is compromised, the script can execute with the agent process's privileges; limiting installation to a missing-CLI error reduces frequency but not the consequences.
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