Security audit
Security checks for vulnerabilities and agentic risk
The Bluesky functions are clearly scoped, but setup can execute unchecked remote code and introduce broader changes to agent skills without clear user control.
Review and approve CLI installation separately, using a verified release, and decide whether additional agent skills may be installed or updated. Upstream documents a startup synchronization control in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Understand that Bluesky requests pass through OOMOL and retain confirmation before posting. The bundled instructions were fully inspected, but the remote installers and service implementation remain unverified.
The supplied code's sole action is remote installer execution, rather than interacting with Bluesky. Dependency installation can be a supporting implementation detail, but this chunk provides no evidence connecting the Oomol installer to the declared functionality. The downloaded script's contents and further effects cannot be determined from the supplied code.
The command streams a mutable remote script directly into Bash without version pinning or independent integrity verification. If the distribution endpoint or delivery pipeline is compromised, attacker-controlled code executes with the agent's local permissions and could access files or credentials; HTTPS alone does not protect against a compromised publisher.
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 the agent to execute downloaded shell or PowerShell code without explicitly requiring user approval or explaining that installation runs code on the host. Although this is a relevant and conditional setup step, it expands a Bluesky task into potentially broad local system changes using unverified remote code.
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