Security audit
Security checks for vulnerabilities and agentic risk
This skill asks before changing Ably data, but its setup can run downloaded software without asking first.
Review and approve CLI installation separately, preferably using a fixed release with verified integrity. Check whether it installs or updates other agent skills. Limit the connected Ably account's permissions and retain the skill's write/delete confirmations. Remote installer and service behavior were not verified; no malicious behavior was established.
The supplied chunk performs remote script execution for an Oomol CLI installer, not Ably data operations. Nothing in the supplied material establishes this installation as a supporting dependency for the declared purpose. The downloaded script's contents and any further effects are unknown.
The supplied code only runs a login command; it does not identify Ably or implement any Ably data operations. Authentication could be a supporting implementation detail if its connection to Ably were established, but the supplied chunk provides no such connection.
Piping a live HTTPS download directly into Bash executes mutable remote code with the invoking user's privileges, without a pinned version or independent integrity verification. Compromise of the installer distribution path could expose local files and credentials or enable persistent host modification; the legitimate OOMOL dependency and setup-only trigger do not eliminate this risk. The PowerShell installation example has the same underlying issue.
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 missing-CLI fallback instructs the agent to execute a remote installer without first explaining its system changes or requesting installation approval. A failed Ably request can therefore escalate into local software installation; the setup-only condition limits exposure, but does not establish informed authorization.
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