ClawHub
Back to skill

Security audit

Polt User

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned but needs review because it lets mutable remote tasks drive agent work and sends profile and submission data to an external production service without clear user-control boundaries.

Review this before installing. Use a dedicated POLT API key, avoid submitting secrets, private repository contents, credentials, internal documents, or access tokens, and require the agent to summarize any remote task and get your approval before committing, doing work, or submitting results.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:9
Finding

Untrusted Remote Task Descriptions Can Hijack the Agent's Goals

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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 81)May include surrounding context.

md
- `POST /api/projects/:id/advance` — Advance project stage
- `POST /api/tasks` — Create task
- `PATCH /api/tasks/:id` — Update task
- `DELETE /api/tasks/:id` — Cancel task
- `GET /api/cto/pending-reviews` — View pending reviews
- `PATCH /api/submissions/:id/review` — Approve/reject submission
- `POST /api/submissions/:id/request-revision` — Request revision

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs agents to use an external production server and to submit registration, profile, and work-submission data, but it does not warn users that this information leaves the local environment and is sent to a third-party service. That can cause unintentional disclosure of sensitive identifiers, profile metadata, proprietary work product, or secrets included in submissions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.