Security audit
Security checks for vulnerabilities and agentic risk
The reporting workflow fits its purpose, but setup can execute unverified downloaded code and introduce undisclosed changes to other agent skills.
Review and approve CLI setup separately before using the skill. Prefer a verified, fixed release and consider disabling automatic skill synchronization with the publisher-documented OO_SKILLS_SYNC_DISABLED setting. OOMOL mediates account access; exact installer behavior and server-side credential handling remain unverified. No malicious behavior was established.
The supplied chunk only downloads and executes a third-party installer; it contains no ClinicalKey operations or evidence connecting the installation to the declared functionality. Although dependency installation can be a supporting implementation detail, that relationship is not established here. The downloaded script is not supplied, so its further behavior cannot be assessed.
The only executable action is an authentication command, and nothing in the supplied chunk connects it to ClinicalKey. Authentication could be a supporting implementation detail, but the provided code does not establish that relationship or implement the declared ClinicalKey functionality.
The command pipes a mutable remote script directly into Bash without version pinning or independent integrity verification. Compromise of the installer host or publishing pipeline could therefore execute attacker-controlled code with the invoking process's privileges; HTTPS alone does not protect against those compromises. The legitimate setup context and command-not-found condition reduce frequency, but not the potential execution impact.
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 the agent to execute downloaded shell or PowerShell code without first explaining the local system changes or requesting installation approval. Although conditional dependency setup is legitimate and reduces exposure, a missing CLI can turn a read-only data request into execution of remotely supplied code with the agent's local privileges.
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