Back to skill

Security audit

TinyURL

Security checks for vulnerabilities and agentic risk

Overview

The TinyURL workflow is coherent, but its setup instructions can execute unpinned remote software without a separate approval or verification step.

Review this skill's setup before enabling it. Prefer a separately reviewed CLI installation, and require approval before executing installers or changing installed agent skills. TinyURL requests pass through OOMOL, where the skill directs you to connect your API key. Preserve its confirmation requirement for link creation. No malicious payload or unrelated data collection was established, but the external installer and connector behavior were not verified.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code installs or runs external software instead of implementing the declared TinyURL functionality. Nothing in the chunk establishes that this installer is a supporting dependency for TinyURL operations. The remote script's contents are not supplied, so its additional behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping a remotely fetched script directly into Bash executes its contents with the agent process's local privileges, without a pinned version or independent integrity verification. Compromise of the installation endpoint or distribution pipeline could lead to local credential theft or arbitrary system changes; HTTPS and the conditional setup trigger do not eliminate this risk. The PowerShell installation example has the same underlying issue.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning the user about remote-code execution or system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-CLI fallback instructs the agent to execute remote installation code without first explaining the local changes or obtaining explicit approval. Restricting this to first-time setup reduces exposure, but the write-confirmation policy only covers TinyURL operations and does not protect this local installation step.

Content

No source excerpt is available for this finding.

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 77)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

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 82)May include surrounding context.

md
## Resources

- TinyURL homepage: https://tinyurl.com
- API documentation: https://api.tinyurl.com/