ClawHub
Back to skill

Security audit

Atris

Security checks for vulnerabilities and agentic risk

Overview

This skill creates and maintains a local code navigation map, with no evidence of hidden execution, credential use, network access, or unsafe persistence.

This is reasonable to install for repository navigation. Treat atris/MAP.md as part of your project documentation: review it before committing or sharing, and make sure it does not include secrets, private paths you do not want disclosed, or sensitive architecture details.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 120)May include surrounding context.

md
- Searching without checking MAP first
- Letting discoveries go unrecorded
- Regenerating the full map when a surgical update would do
- Including secrets, credentials, or .env files in the map
- Guessing file locations instead of using the index

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 117)May include surrounding context.

md
## Anti-patterns

- Searching without checking MAP first
- Letting discoveries go unrecorded
- Regenerating the full map when a surgical update would do
- Including secrets, credentials, or .env files in the map

Static analysis

No suspicious patterns detected.