Back to skill

Security audit

update-skill

Security checks for vulnerabilities and agentic risk

Overview

The skill has approval gates for updates, but its cleanup instructions can delete unrelated files without specific permission.

Before using this skill, change cleanup to remove only files it demonstrably created and require explicit permission for unknown paths. Protect concurrent work in the main checkout. Review private-conversation access and the target repository's validation and publishing commands; those external runtime components were not included in this review.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

md
upstream: "keep-a-changelog@2.0.0"
---

# Update Skill

Run a thorough on-demand refresh of one skill in a skills repository. Two hard human-approval gates ensure no edits or commits happen without explicit confirmation.

Checkout hygiene authorizes deletion of unrelated new files outside the target skill.

High
Category
Excessive Agency
Confidence
99% confidence
Finding

The hygiene rule assumes every newly appearing path outside the target skill and generated README belongs to this run, then instructs the agent to remove it in both the worktree and main checkout. Concurrent user activity or another agent can create legitimate files after the baseline snapshot, so this can delete unrelated, potentially unrecoverable untracked data before the second approval gate.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.