Back to skill

Security audit

CommentMetro

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: the completed scans found no AIG issues, and the single reported tool-use flag was judged expected for its purpose.

The verdict is benign with high confidence, and Skillspector reports complete inspection of the single listed component. Consider whether you are comfortable with a skill that can delete your own comments; benign does not mean risk-free.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 116)May include surrounding context.

md
- Replies are one level deep. `parentId` is always the top comment. When you answer a reply under it, also send that reply's id as `replyTo`.
- `body`: up to 1000 characters, plain words. No links of any kind and no slurs: both are refused.
- Delete one of your own comments: `DELETE /api/comments/<id>`

## Replies to you