Security audit
Security checks for vulnerabilities and agentic risk
This integration needs review because it treats order submissions as reads and directs automatic execution of an unverified installer when its CLI is missing.
Before use, require approval of screening payloads, customer-data sharing through OOMOL, and credit consumption. Install a reviewed, fixed CLI release separately and check its automatic skill synchronization settings. The external installer and connector implementation were not verified; the bundled skill shows no evidence of intentional malicious behavior.
The supplied command runs a remote installer rather than accessing FraudLabs Pro data. Nothing in the chunk establishes that this installation supports the declared integration. The downloaded script's contents are not supplied, so its further effects cannot be determined.
The supplied code only initiates a CLI login. It contains no FraudLabs Pro reference or data operations, and nothing establishes that this authentication is a supporting step for FraudLabs Pro. The visible behavior therefore does not substantiate the declared purpose. The service targeted by oo cannot be determined from this chunk.
Piping a mutable HTTPS response directly into bash executes remote code without verifying its contents or release identity. Compromise of the installer delivery path could yield arbitrary code execution with the agent's local privileges; HTTPS and a legitimate dependency relationship do not eliminate that supply-chain risk.
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 blanket rule that untagged actions are reads incorrectly includes screen_order, which submits an order for processing rather than merely retrieving an existing result. Screening can create a transaction, transmit sensitive order information, and consume service quota or credit, so this classification bypasses the skill's own confirmation safeguard.
A missing CLI triggers instructions to install software by immediately executing a downloaded script, without an explicit approval checkpoint or integrity verification. This can modify the host and execute arbitrary code with the invoking user's privileges; the missing-command condition limits exposure but does not authorize those changes.
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