Security audit
Security checks for vulnerabilities and agentic risk
The Pushbullet workflow has sensible safeguards, but setup directs downloaded code execution without a clear approval step.
Review and approve CLI installation separately, using a verified release. Check its automatic skill synchronization before first use; the [CLI reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) documents OO_SKILLS_SYNC_DISABLED. OOMOL brokers access to your Pushbullet account, so connect only an account you intend to expose and retain the skill's confirmations for sending, changing, and deleting data.
The supplied chunk performs no visible Pushbullet operations and instead executes an installer from a different service. Nothing supplied establishes that this is a supporting dependency for the declared purpose. The remote script's contents and downstream behavior are not available for assessment.
Piping an HTTPS response directly into bash executes mutable remote code without checking a pinned version, signature, or independently trusted digest. Compromise of the installation endpoint or its publishing pipeline could therefore lead to arbitrary code execution and access to local data available to the agent. The endpoint is relevant to the required CLI and uses HTTPS, which reduces suspicion but does not establish script integrity.
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 directs installation through immediately executed remote scripts without requiring disclosure of local changes or explicit installation approval. A request to manage Pushbullet data does not necessarily authorize installing software, and these scripts can execute with the agent process's local permissions. The conditional fallback limits exposure, but the confirmation rules for Pushbullet writes do not cover local installation.
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