Back to skill

Security audit

Ably Control

Security checks for vulnerabilities and agentic risk

Overview

The Ably operations have approval safeguards, but setup executes unverified remote code and leaves additional agent-skill installation behavior unexplained.

Review the CLI installation before allowing setup to run. Choose and verify a CLI release yourself, and consider setting OO_SKILLS_SYNC_DISABLED=1 before invocation to prevent automatic agent-skill changes. Use narrowly scoped Ably credentials and protect returned key data. The remote installer and hosted connector implementation were not inspected, so their exact behavior remains uncertain.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs remote software installation rather than the declared Ably Control data operations. Nothing in the supplied chunk establishes that this installer supports the stated purpose. The downloaded script's contents and further effects are not visible.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

md
- `delete_queue` — Delete an Ably queue by queue ID. [destructive]
- `get_account_stats` — Retrieve account-level Ably statistics for the connected account or account ID.
- `get_app_stats` — Retrieve app-level Ably statistics for an Ably app.
- `get_current_account` — Retrieve the Ably Control API token, user, and account associated with the access token.
- `list_apps` — List Ably apps in the connected account or supplied account ID.
- `list_keys` — List API keys for an Ably app.
- `list_queues` — List queues for an Ably app.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup instructions pipe a mutable remote script directly into Bash, and the Windows alternative similarly executes downloaded content without integrity verification. Although this is relevant dependency setup and only triggered when the CLI is missing, compromise of the installer distribution could execute arbitrary code with the agent's local privileges.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

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.

Content

Scanner excerpt · SKILL.md (reported line 89)May include surrounding context.

md
- **`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