ClawHub
Back to skill

Security audit

SpecStream: Read and Send Results

Security checks for vulnerabilities and agentic risk

Overview

The skill’s instructions fit its purpose, with user-requested sharing and explicitly bounded recurring monitors.

Use a SpecStream connection you trust, confirm the selected results and destination before sharing, and review prices and monitor limits before starting new work. The complete bundled artifact was inspected, but the remote service's permissions, data handling, and enforcement were not verified.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

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 9)May include surrounding context.

md
# Read, send and continue

SpecStream is the live web data engine for teams and agents. Use the configured MCP server at `https://api.specstream.ai/mcp`.

Read `list_find_rows` and follow each `next_cursor` through the `cursor` argument until it is null. The first page is not the whole result. Open `get_find_decisions` to show each condition check with the value observed, its source and the time it was read. Never invent links or fill in unknown facts. Keep the original read times and do not call reused evidence fresh.