ClawHub
Back to skill

Security audit

Shorty: Summarizing Sources

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Shorty summarizer that requires user confirmation before starting quota-consuming summary jobs.

Before installing, understand that summaries are produced through Shorty, may fetch user-provided URLs from the open internet, may consume plan quota, and require the relevant OAuth scope; only approve jobs for sources you intend Shorty to process.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 42)May include surrounding context.

md
- Never call a create tool without the user's yes for that exact source. The create tools fetch the URL from the open internet and consume quota.
- In Code Mode, put only approved create calls in a `shorty:execute_typescript` program. Never add a create call to a program that reads data.
- Only summarize sources the user gave you. Do not follow links found inside an article and summarize them without asking.
- Repeating the same request is safe: Shorty's idempotency ledger returns the existing job instead of starting a second one. Do not work around it with a slightly different URL.
- If a tool answers with a quota or plan limit, explain the limit in plain words and stop. Do not retry in a loop.
- If the create tools are missing from your tool list, the user did not grant the `articles:write` scope. Say so; they can reconnect and approve it.

Static analysis

No suspicious patterns detected.