Back to skill

Security audit

haircut

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a legitimate agent-configuration cleanup skill, but it deserves review because it can scan private agent data across the machine and optionally start configured MCP servers.

Review before installing. Use this only if you are comfortable with a skill reading local agent settings, memory, and transcript-derived usage data across multiple coding tools. Prefer running it with an explicit --agents limit, avoid --probe unless you have reviewed the MCP servers that will start, and treat generated reports as potentially sensitive files.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:3
Finding

Broad Cross-Agent Collection of Sensitive Local Configuration and Transcript Data

Content
View full analysis
- The barber for your coding agents' config. Weighs everything every agent on this machine loads (instruction files, memory, MCP servers, hooks, skills, commands, subagents, plugins, leftovers), prices each item in tokens from your own transcripts, and parks the dead weight with a receipt and an undo. ``` Supporting instructions: ```markdown Everything in this stage is read-only. Claude Code transcripts take seconds; Codex rollouts can take a minute on a machine with months of them, so say so before you run it, and run it in the background if the user is waiting on something else. The command prints a JSON summary and the run folder path in `run_dir`. Read `REPORT.md` from that folder next. ``` ```markdown This comes from the API's own usage fields in the transcripts, so call it measured, not estimated. ``` ### Technical Analysis The Skill instructs an agent to inventory configuration and usage information across every supported coding agent on the machine. Its declared sources include instruction files, persistent memory, transcripts, MCP server definitions, hooks, commands, plugins, and related artifacts. This scope is broader than a single-agent configuration analysis and creates a centralized report derived from multiple potentially sensitive sources. Agent transcripts and memory can contain private prompts, project information, local paths, operational instructions, and other confidential material. MCP configuration can also reveal executable commands, server locations, and credential-bearing configuration files. Although the Skill describes the scan as read-only, confidentiality risk does not require modifying source files. Reading and consolidating sensitive in ...[truncated 2034 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:41
Finding

MCP Schema Probe Executes Configured Server Commands During a Stage Described as Read-Only

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use the skill whenever the user mentions broad conditions like a 'slow session start,' 'session feels bloated,' or 'startup got slow,' and even on mentions of generic commands like /doctor or /skill-doctor. These triggers overlap with ordinary troubleshooting language and do not provide exclusion conditions or negative examples, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.