Security audit
Security checks for vulnerabilities and agentic risk
The Bland AI reads fit the stated purpose, but the required CLI can also change other agents’ installed skills without this skill explaining those changes.
Review the CLI’s broader installation effects before proceeding. Prefer a verified release and explicitly approve installation. If cross-agent skill changes are unwanted, configure OO_SKILLS_SYNC_DISABLED=1 before CLI use, after checking version support; the [publisher’s startup source](https://github.com/oomol-lab/oo-cli/blob/main/src/application/bootstrap/run-cli.ts) implements this control. Connecting Bland AI also entrusts OOMOL with access to your account data. Remote installer bytes and the exact installed release were not verified; no malicious intent was established.
The supplied chunk contains no Bland AI search or read operations. Its sole action is to fetch and execute an external installation script. This is a materially different operation from the declared purpose, with no demonstrated supporting relationship to Bland AI. The remote script's contents and further effects are not available for assessment.
Authentication could support a data-access skill, but the supplied chunk contains only a login command and no Bland AI search or read behavior. Its implemented purpose therefore materially differs from the declared purpose. The chunk does not establish which service is authenticated or how credentials are handled.
The curl-to-bash pipeline immediately executes whatever script the installation endpoint supplies, without pinning a version or independently verifying its integrity. HTTPS protects transport but does not prevent a compromised publisher or hosting pipeline from supplying code that could steal local data or modify the environment; this is the same underlying installation risk identified by 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 fallback setup directs the agent to execute remotely downloaded shell or PowerShell scripts without prior review, integrity verification, or explicit installation approval. If the distribution endpoint or delivery pipeline is compromised, the script can execute arbitrary code with the agent's local permissions; the conditional setup trigger reduces exposure but does not remove this risk.
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