Security audit
Security checks for vulnerabilities and agentic risk
The Prospeo integration fits its purpose, but its setup fallback can run unverified downloaded code without separate user approval.
Install and verify oo separately, and require approval before the agent runs either setup installer. Review the CLI's additional skill-installation behavior and send only necessary identifiers through OOMOL to Prospeo. The exact remote installer changes remain unverified; no malicious behavior was established.
The supplied chunk performs remote installer execution, not the declared Prospeo data operations. No visible integration establishes this installer as a supporting dependency for Prospeo. The downloaded script is not supplied, so its further behavior cannot be determined.
Piping a mutable remote installer directly into bash executes its contents without prior inspection or verification of a pinned artifact. HTTPS reduces transport interception risk but does not protect against a compromised publisher or distribution system; exploitation could expose local files, credentials, and writable resources available to the process.
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 submit action payloads through OOMOL to Prospeo; enrichment inputs can include identifying person and company information. Although the connector architecture is described, the skill does not warn users that information supplied in these payloads is transmitted to external services.
The missing-CLI fallback directs the agent to execute downloaded shell or PowerShell code without an explicit approval step, integrity verification, or an opportunity to inspect it. Although conditional and relevant to setup, this can turn an ordinary read request into local code execution with the agent's permissions if the installer delivery path is compromised.
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