ClawHub
Back to skill

Security audit

merge-drafts

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward document-merging workflow with explicit limits around input handling, file replacement, and external delivery.

Before installing, review the README install commands and only run the ones for agents you actually use. When using the skill, provide only drafts or documents you are authorized to merge, because it may read private documents through already-authorized host connectors.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 37)May include surrounding context.

md
- DOCX/PDF extraction and HTML/PDF export depend on the host's existing tools.
  They are not bundled or claimed tested by this package.
- Ancillary analysis is used only when included or clearly relevant to the task.
- Markdown/text is the default. Preserve original inputs and write a separate
  result unless replacement is explicitly authorized.
- External delivery or publishing requires explicit authorization for the target.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 72)May include surrounding context.

absent. Use the selected Hermes profile's home:

sh
mkdir -p ~/.claude/skills "${HERMES_HOME:-$HOME/.hermes}/skills"
ln -s "$HOME/.agents/sources/merge-drafts" "$HOME/.claude/skills/merge-drafts"
ln -s "$HOME/.agents/sources/merge-drafts" "${HERMES_HOME:-$HOME/.hermes}/skills/merge-drafts"

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 72)May include surrounding context.

absent. Use the selected Hermes profile's home:

sh
mkdir -p ~/.claude/skills "${HERMES_HOME:-$HOME/.hermes}/skills"
ln -s "$HOME/.agents/sources/merge-drafts" "$HOME/.claude/skills/merge-drafts"
ln -s "$HOME/.agents/sources/merge-drafts" "${HERMES_HOME:-$HOME/.hermes}/skills/merge-drafts"

Static analysis

No suspicious patterns detected.