Security audit
Security checks for vulnerabilities and agentic risk
The Maps features fit their purpose, but setup can execute unverified downloaded code and introduce changes to other agent skills without clear approval.
Review and approve CLI installation separately before allowing the fallback. Consider disabling automatic skill synchronization using the documented OO_SKILLS_SYNC_DISABLED setting in the [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Your Maps queries pass through OOMOL. The downloaded installers and server behavior were not verified; no malicious behavior was established in the inspected artifact.
Installing the documented connector CLI is related to the skill's operation, so accessing a non-Apple domain is not inherently suspicious. However, the fallback expands a read-only Maps request into executing mutable remote installer code locally without explicit approval or integrity verification; a compromised installer could execute arbitrary commands with the agent's privileges.
The supplied code's sole behavior is a login command, rather than the declared Apple Maps functionality. Authentication could be a supporting implementation detail, but this chunk provides no evidence connecting that workflow to Apple Maps.
The command immediately executes whatever script the remote endpoint returns, without pinning a version or verifying an independently trusted signature or digest. HTTPS protects transport but not against compromise of the distribution endpoint, which could result in arbitrary code execution with the invoking process's privileges.
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 installation through downloaded shell or PowerShell code without explaining the local changes or requesting approval. Although triggered only when the CLI is missing, it crosses from reading Maps data into local code execution and exposes the host to installer compromise.
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