Security audit
Security checks for vulnerabilities and agentic risk
The email lookup workflow fits its purpose, but setup can execute unchecked remote code and introduce persistent changes to other agent skills.
Review and verify the CLI installation before allowing the fallback commands. Contain its persistent skill changes: upstream documents OO_SKILLS_SYNC_DISABLED=1 for disabling startup synchronization. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Submit only lookup details you authorize sharing with OOMOL and Anymail Finder, and consider available credits. The remote installers and live connector implementation remain unverified; no malicious intent was established.
The supplied command contains no Anymail Finder interaction and instead executes an installer hosted on an unrelated domain. Nothing supplied establishes this installation as a supporting dependency for the declared purpose. The downloaded script's contents are unavailable, so its further behavior cannot be determined.
The supplied code performs only authentication, not Anymail Finder searches or data retrieval. Authentication could be a supporting implementation detail, but nothing in this chunk connects the oo login to Anymail Finder or establishes it as a prerequisite for the declared functionality.
The setup command pipes a remotely fetched, unpinned script directly into Bash without an independent integrity check or review; the PowerShell alternative has the same execution pattern. If the distribution endpoint or release infrastructure is compromised, an agent following this fallback could execute attacker-controlled code with its process privileges, exposing local files and credentials. Its conditional setup context reduces exposure but does not remove the 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 workflow instructs the agent to submit action payloads through OOMOL to Anymail Finder; the supported actions include searches using a person's name, company, LinkedIn profile, or email address (lines 40–44). Although the connector is identified, the skill does not warn that these personal details leave the user's environment, and line 48 broadly labels untagged actions safe to run directly.
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