ClawHub
Back to skill

Security audit

US Market Briefing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed US market-briefing helper with limited optional automation and no evidence of hidden exfiltration, destructive behavior, or prompt-theft instructions.

Before installing, confirm you are comfortable with the skill using web search/fetch for finance sources and, if you enable scheduled delivery, review the OpenClaw cron job it creates. Consider replacing the 'Kevin' early-close exception with an explicit user-controlled setting.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

There is a clear description-behavior mismatch. The declared purpose centers on producing full US market briefings from news and market data, but the actual code only parses an optional date argument, looks it up in a hardcoded 2026 holiday calendar, and emits a JSON market-open status. While holiday checking could be a supporting helper within a broader market-briefing system, this code chunk by itself does not implement the declared primary functionality and instead serves a materially different, much narrower purpose.

Content

No source excerpt is available for this finding.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
- Do not edit system cron (`crontab`, `/etc/crontab`) and do not configure external schedulers/services.
- If schedule tooling/scope is unclear, ask for explicit user approval before creating or changing jobs.

## Output Rules

- Keep exactly 3 sections for each briefing.
- Keep canonical section names by default; if user explicitly asks for custom headings/branding, allow aliases while preserving the same 3-section structure.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The instruction 'Treat early-close as market-open unless Kevin says otherwise' embeds a named approver into operational logic without any authenticated authorization model. This creates ambiguous trust boundaries and could let an agent defer to undocumented, non-user-approved policy, increasing the risk of unauthorized or inconsistent automation behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.