Security audit
Security checks for vulnerabilities and agentic risk
The image-generation workflow fits its purpose, but the required CLI can silently install or refresh other agent skills without this skill explaining those changes.
Review the CLI installation separately and decide whether it may manage skills across your agents. Its documentation provides OO_SKILLS_SYNC_DISABLED=1 to disable startup synchronization. Use public image URLs you intend to share and account for usage credits. The exact remote installer and hosted connector implementation were not verified.
The supplied command executes an external installation script, with no demonstrated connection to Alt Text Generator AI or its declared search/read functionality. This introduces undeclared remote-code execution and installation behavior. The downloaded script's exact effects cannot be determined from the supplied chunk.
The supplied code contains only a login command, with no Alt Text Generator AI resource reference or search/read behavior. Authentication could support the declared functionality, but the chunk provides no evidence of that connection; its sole demonstrated purpose is initiating login.
Piping a mutable HTTPS download directly into Bash executes the returned content without a review or integrity-check step. The OOMOL domain is relevant to the documented integration, but that does not prevent installer or distribution compromise from becoming arbitrary code execution in the agent's environment.
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 directs the agent to execute downloaded shell or PowerShell code without explicit approval for the resulting system changes or any integrity verification. Although conditional setup makes this less suspicious, a compromised installer endpoint or distribution pipeline 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