Security audit
Security checks for vulnerabilities and agentic risk
The image workflow fits its purpose, but setup directs execution of unverified remote code without clearly controlling broader changes to your agent environment.
Review and install a fixed CLI release yourself before using this skill, and require approval for setup changes. Check the CLI's automatic skill synchronization settings because it can affect other installed agents. Image requests pass through OOMOL to the connected provider and may consume credits. The remote installers could not be inspected, so their exact changes remain uncertain; no malicious behavior was established.
The only demonstrated behavior is remote installer execution, not interaction with Doubao Seedream. Dependency installation could be a supporting implementation detail, but the supplied content does not establish that this installer supports the declared purpose. The downloaded script is not provided, so its additional effects cannot be determined.
Piping an HTTPS response directly into bash executes mutable remote content without independent integrity verification or review. The domain is consistent with the documented CLI provider, so there is no evidence of malicious intent, but a compromised hosting or release pipeline could run arbitrary commands and access local files or credentials; the PowerShell example has the same 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 missing-CLI fallback directs the agent to execute downloaded shell or PowerShell code without first explaining the system changes or obtaining installation-specific approval. The fallback-only condition limits exposure, but the write-action confirmation requirement does not explicitly cover this local installation, which could execute arbitrary code with the invoking 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