Security audit
Security checks for vulnerabilities and agentic risk
The Vida workflow is coherent, but automatic installation and undisclosed changes to other agent skills warrant review.
Review and install the CLI separately before using this skill, and decide whether OOMOL should manage additional agent skills. The publisher documents OO_SKILLS_SYNC_DISABLED=1 to disable startup synchronization. Connecting Vida entrusts OOMOL with its credentials and account access. The bundled instructions were fully inspected, but the remote installers and released binary were not verified.
The supplied chunk runs an Oomol installer and contains no Vida search or reading functionality. Although dependency installation can be a supporting implementation detail, nothing supplied establishes this installer's relationship to Vida. The remote script's contents are unavailable, so its additional behavior cannot be determined.
The supplied chunk only invokes a login command; it contains no Vida search or read operations and establishes no connection between oo and Vida. Authentication could be a supporting implementation detail, but the supplied code presents it as the entire behavior rather than as part of the declared functionality.
Piping a mutable remote script directly into bash executes its contents with the agent process's local privileges without prior verification or review. HTTPS protects transport but does not prevent a compromised publisher or distribution endpoint from serving malicious code; the PowerShell setup command has the same underlying 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 fallback instructs the agent to execute remotely supplied shell or PowerShell code without first explaining the local changes or obtaining explicit installation approval. Although installation supports the legitimate connector workflow and occurs only when the CLI is missing, a read-oriented Vida request should not implicitly authorize arbitrary local installer execution.
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