Back to skill

Security audit

SpecStream: See the Price

Security checks for vulnerabilities and agentic risk

Overview

The skill requests price quotes and balance checks from a disclosed service while explicitly preserving user control over spending.

Use a SpecStream MCP connection you trust and expect request identifiers and quote parameters to reach that provider. Keep quoting separate from spending authorization. This review covers the bundled instructions, not the remote server's implementation, authentication, or retention practices.

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
  • 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
# See the price

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

Call `quote_capacity_work` with the `ast_hash` from `compile`, the operation, the number of results wanted, the useful minimum, and the original `parent_find_id`, `project_id` or `revision_id` when one applies. Asking for more uses `extend`, adding facts uses `add_facts` and rechecking uses `refresh`.