Security audit
Security checks for vulnerabilities and agentic risk
The KIE.AI features fit the stated purpose, but setup can execute unverified downloaded code and make broader changes to your agent’s skills.
Review and approve CLI setup separately before enabling this skill. OOMOL mediates account access and stores the connected provider credentials. Consider disabling automatic skill synchronization using OO_SKILLS_SYNC_DISABLED=1, as documented in the publisher’s command reference. Remote installer contents and the downloaded release were not verified; no malicious payload was established.
The supplied command performs remote installer execution rather than KIE.AI search or data retrieval. Nothing in the supplied code establishes that this installer is a supporting dependency for the declared purpose. The downloaded script's contents and resulting system changes cannot be determined from this chunk.
Authentication can be a supporting implementation detail, but the supplied code contains only a login command and no demonstrated KIE.AI integration or data-access behavior. Its observable primary purpose therefore differs from the declared purpose.
Piping the HTTPS response directly into bash executes whatever the installation endpoint supplies without pinning or verifying the code. A compromised distribution endpoint or altered installer could execute arbitrary commands with the agent's permissions, potentially exposing local credentials or modifying files; HTTPS alone does not protect against compromise of the publisher's distribution infrastructure.
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
When the CLI is missing, the skill directs the agent to execute a downloaded installer without a separate approval step or a stated integrity-verification procedure. This crosses from reading account data into executing code with the agent process's local permissions; the missing-command prerequisite reduces exposure but does not constrain what the installer can change or access.
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