Security audit
Security checks for vulnerabilities and agentic risk
The Logo.dev workflow is coherent, but its setup directs the agent to execute remote installers without integrity checks or clear user approval.
Review the setup before enabling this skill. Install a verified, version-pinned CLI yourself and approve its local changes, including any bundled-skill synchronization. Connect only the intended Logo.dev account through OOMOL. The mismatch and billing allegations are unsupported by the complete skill text; the concrete concern is automatic remote-code installation with incompletely disclosed effects. The hosted connector and installer implementations are outside the inspected artifact.
The supplied command performs remote script execution for an Oomol CLI installer rather than searching or reading Logo.dev data. No relationship to Logo.dev is established, and installing software is not a declared capability or a demonstrated supporting implementation detail. The downloaded script's exact effects cannot be determined from this code chunk.
The supplied chunk performs only a login operation. Although authentication can support API access, nothing here connects this command to Logo.dev or implements the declared search/read functionality. The visible behavior therefore materially differs from the declared purpose.
Piping an HTTPS download directly into bash executes mutable remote content without checking a pinned version, signature, or expected digest. Compromise of the distribution endpoint could therefore produce arbitrary code execution with the agent's local privileges; the missing-CLI condition limits exposure but does not remove this 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 fallback setup instructs the agent to execute downloaded shell or PowerShell code without explaining the resulting local code execution or requiring explicit installation approval. Although conditional and relevant to the connector, this expands a read-oriented task into potentially broad system changes under the executing user's privileges.
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