ClawHub
Back to skill

Security audit

COMMS.md Reader

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped communication-preference reader that tells the agent to use only user-approved COMMS.md sources and does not include code, persistence, or hidden authority.

Before installing, understand that the skill helps tailor outgoing messages using a recipient's stated preferences. Use it only with COMMS.md files or URLs you trust and approve, and review the final draft before sending, especially if the recipient's file contains unusual instructions beyond communication preferences.

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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
55% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 74)May include surrounding context.

md
1. **Match their closeness tier.** Determine the relationship: close friend, professional contact, new outreach, re-engagement after a gap. Use the conventions from their matching tier.
2. **Mirror their mechanics.** If they prefer lowercase casual, don't send proper-capped formal prose. If they hate exclamation points, don't use them.
3. **Apply their warm competence signals.** For new/professional contacts: use their name once, reference something specific, close warm not transactional.
4. **Avoid their anti-patterns.** If they list "don't apologize for reaching out" — don't open with "Sorry to bother you." If they say no corporate speak — no "just circling back."

### Call Framing