ClawHub
Back to skill

Security audit

AI PM Intel Brief

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only AI product-manager briefing skill that summarizes recent public social posts and does not include hidden code, persistence, or credential handling.

Before installing, expect this skill to guide the agent toward collecting and summarizing recent public social posts for AI product-management briefs. If you prefer English or another format, state that explicitly because the included template is Chinese-first.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill description includes broad trigger phrases such as generic requests for news briefs, roundups, and post summaries, which can cause the router to invoke this skill for loosely related requests outside its intended niche. This creates scope overreach: the skill may capture unrelated user intents, leading to incorrect tool use, unwanted external data collection, or summaries in contexts where a different skill should handle the request.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The recommended output structure hardcodes Chinese headings and date/title conventions without stating that the skill is Chinese-first or allowing language selection. This can override user language expectations and cause unintended output shaping, which is a scope and usability problem that may misroute or degrade responses, though it is not a direct code-execution or data-exfiltration issue.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The template headings and output structure are entirely in Chinese, which implicitly requires responses in a specific language. Under the policy, language constraints should either be optional for the user or clearly documented as justified for a region-specific use case.

Static analysis

No suspicious patterns detected.