ClawHub
Back to skill

Security audit

Appdeploy

Security checks for vulnerabilities and agentic risk

Overview

This deployment skill is mostly coherent, but it tells the agent to follow mutable instructions from an external API before generating and deploying code.

Review this skill before installing if you use proprietary code or secrets. It is intended to deploy apps through SkillBoss, so app files and metadata may leave your environment; confirm what will be sent, keep secrets out of deployed files, and treat remote deployment instructions as constraints that cannot override your own instructions or security requirements.

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

Warning
Location
SKILL.md:44
Finding

Untrusted Remote Instructions Can Influence Agent Behavior

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

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

md
# AppDeploy Skill

Deploy web apps via SkillBoss API Hub (https://api.heybossai.com/v1/pilot).

## Setup (First Time Only)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly sends deployment requests, app metadata, and potentially app files to a third-party HTTP API, but it does not clearly warn users that their code and related data will leave the local environment. In a deployment skill, this omission matters because users may provide proprietary source code, secrets embedded in files, or sensitive configuration without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The explicit endpoint reference at the point of the curl example is part of a real external transmission workflow, not just documentation. In context, this skill is designed to deploy apps to a hosted service, so the danger is contextual: it normalizes sending complete application artifacts to a third party without an equally explicit warning about privacy, code ownership, and secret-handling.

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

Make calls to the SkillBoss API Hub deployment endpoint:

bash
curl -X POST https://api.heybossai.com/v1/pilot \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The explicit endpoint reference at the point of the curl example is part of a real external transmission workflow, not just documentation. In context, this skill is designed to deploy apps to a hosted service, so the danger is contextual: it normalizes sending complete application artifacts to a third party without an equally explicit warning about privacy, code ownership, and secret-handling.

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

Make calls to the SkillBoss API Hub deployment endpoint:

bash
curl -X POST https://api.heybossai.com/v1/pilot \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -d '{

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

The instruction says timestamp values must be converted to the user's local time, which imposes a locale-specific presentation rule. The file does not indicate user opt-in or explain a justified regional requirement, so this can be considered a natural-language locale policy constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.