Security audit
Security checks for vulnerabilities and agentic risk
The Missive reading features fit their purpose, but setup permits unverified remote code execution and insufficiently disclosed changes to other agent skills.
Review CLI installation separately before allowing setup, and prefer a pinned, verified release. Consider disabling automatic skill synchronization using OO_SKILLS_SYNC_DISABLED=1 as documented in the [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Connect only the Missive account access you need and understand that OOMOL handles the integration. The remote installers and live connector implementation were not verified; no malicious behavior was established.
The supplied chunk performs remote installer execution rather than accessing Missive data. Although installation can be a supporting implementation detail, this chunk provides no evidence that the Oomol installer supports the declared Missive purpose. The downloaded script's contents and any further effects cannot be determined from the supplied code.
The command pipes a mutable remote script directly into Bash without pinning a release or independently verifying its integrity; the PowerShell alternative uses the same download-and-execute pattern. Compromise of the distribution endpoint could therefore execute attacker-controlled code with the agent process's local permissions, although the documented vendor domain and conditional setup make this a supply-chain risk rather than evidence of malicious intent.
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
A missing CLI triggers instructions to install software through immediate execution of downloaded code, without requiring informed user approval for host changes. Although this is a legitimate prerequisite and only a fallback, a read-oriented Missive request does not itself authorize potentially broad local installation effects.
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