Security audit
Security checks for vulnerabilities and agentic risk
The OCR workflow is coherent, but its automatic setup executes unverified remote code and can introduce broader, persistent changes to agent skills.
Review and install a verified CLI release yourself before using this skill, and disable unwanted automatic skill synchronization. Send only documents you intend OOMOL and OCR.space to process, and check applicable charges. The bundled document was fully inspected, but the remote installers and hosted connector implementation were not verified.
The supplied command performs remote script execution rather than an OCR.space operation. Nothing in the provided chunk establishes that installing this software is a supporting requirement for the declared purpose. The downloaded script's contents are not supplied, so its further behavior cannot be determined.
Authentication can be a supporting implementation detail, but the supplied chunk contains only a login command and shows no connection to OCR.space or its declared operations. On the available evidence, its primary behavior differs materially from the description.
The fallback pipes a mutable remote script directly into Bash without pinning its contents or verifying an independently trusted signature or digest; the PowerShell alternative has the same issue. If the distribution endpoint or release pipeline is compromised, invoking setup could execute attacker-controlled code with the agent's local privileges and expose accessible files or credentials. Its conditional use and relevant vendor domain reduce exposure but do not ensure script integrity.
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 run connector actions with supplied payloads, including extract_text with an uploaded Base64 file. Although the catalog identifies OCR.space as the processor, the safety section labels untagged actions safe to run directly without warning that image contents, potentially including sensitive information, are transmitted to a third-party service.
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