Security audit
Security checks for vulnerabilities and agentic risk
The Make workflow has sensible approval controls, but its setup instructs the agent to execute unverified downloaded software without separate approval.
Review and approve CLI installation separately before allowing setup. Prefer a verified release and review or disable automatic agent-skill synchronization; the documented OO_SKILLS_SYNC_DISABLED control addresses synchronization. Connect only the Make permissions needed and retain confirmation for scenario changes and runs. OOMOL handles the connected credentials and requests. The remote installers were unavailable for inspection, so their complete effects remain uncertain.
The supplied command performs remote code execution for an apparent Oomol CLI installation, with no visible Make functionality or evidence that this installation supports Make operations. This is a material mismatch, rather than an established supporting implementation detail. The remote script's further behavior cannot be determined from this chunk.
Piping a remotely fetched, unpinned script directly into Bash executes its contents without an integrity or authenticity check beyond HTTPS. Compromise of the distribution endpoint could lead to arbitrary code execution, credential theft, or modification of files accessible to the agent; the legitimate CLI setup context does not remove that 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 instructs the agent to install software by immediately executing downloaded scripts, without first explaining local system changes or obtaining installation approval. Although conditional on the CLI being absent, a Make operation does not necessarily authorize arbitrary local installation, and a compromised installer could execute with the agent's permissions.
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