ScrapeSense.com Developer

• Outcome: Review
• Latest audit: Sep 10, 2026 · 9:19 PM UTC
• Version: 1.0.1

Overview

The skill is a coherent ScrapeSense API helper, but it covers destructive, bulk-email, API-key, and webhook operations with limited safety guidance.

Review this skill before installing if you plan to let an agent act on your ScrapeSense account. Use least-privilege API keys, require explicit confirmation for delete, billing, webhook, key-management, and bulk-send actions, and avoid exposing raw keys or webhook secrets in prompts or logs.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Tool Misuse: Tool Parameter Abuse, Chaining Abuse, Unsafe Defaults
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (10)

Ae1

High

• Category: analysis-evasion

Content

- Keep skill developer-focused (`SKILL.md` + API references only).

• Confidence: 100% confidence
• Finding: Referenced artifact was not completely inspected

Tool Parameter Abuse

High

• Category: Tool Misuse

Content

## Scans
- `GET, POST /scans`
- `GET, DELETE /scans/{id}`
- `GET /scans/{id}/tiles`
- `POST /scans/{id}/pause`
- `POST /scans/{id}/resume`

• 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).

Tool Parameter Abuse

High

• Category: Tool Misuse

Content

- `GET, POST /campaigns`
- `POST /campaigns/create`
- `GET /campaigns/stats/summary`
- `GET, DELETE /campaigns/{id}`
- `GET /campaigns/{id}/emails`
- `GET, PUT, DELETE /campaigns/{id}/emails/{emailId}`
- `POST /campaigns/{id}/emails/{emailId}/approve`

• 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).

Tool Parameter Abuse

High

• Category: Tool Misuse

Content

- `GET /campaigns/stats/summary`
- `GET, DELETE /campaigns/{id}`
- `GET /campaigns/{id}/emails`
- `GET, PUT, DELETE /campaigns/{id}/emails/{emailId}`
- `POST /campaigns/{id}/emails/{emailId}/approve`
- `POST /campaigns/{id}/emails/{emailId}/send`
- `POST /campaigns/{id}/start`

• 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).

Tool Parameter Abuse

High

• Category: Tool Misuse

Content

- `POST /campaigns/{id}/emails/{emailId}/regenerate`
- `POST /campaigns/{id}/regenerate-all`
- `POST /campaigns/{id}/retry-failed`
- `DELETE /campaigns/{id}/places/{placeId}`
- `POST /campaigns/{id}/test-prompt`
- `POST /campaigns/{id}/preview`

• 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).

Tool Parameter Abuse

High

• Category: Tool Misuse

Content

## Developer API Keys
- `GET, POST /developer/keys`
- `PATCH, DELETE /developer/keys/{id}`
- `GET /developer/keys/{id}/usage`

## Developer Webhooks

• Confidence: 80% confidence
• Finding: Developer key management endpoints are materially more sensitive than ordinary CRUD operations because deleting or modifying keys can revoke access, disrupt integrations, or facilitate unsafe key lifecycle handling if an agent uses them casually. In a developer-focused skill, listing these endpoints without prominent cautions around least privilege, secure storage, rotation procedures, and confirmation increases the chance of credential-management mistakes with high operational impact.

Tool Parameter Abuse

High

• Category: Tool Misuse

Content

## Developer Webhooks
- `GET /developer/webhooks/events`
- `GET, POST /developer/webhooks`
- `PATCH, DELETE /developer/webhooks/{id}`
- `POST /developer/webhooks/{id}/test`
- `GET /developer/webhooks/{id}/deliveries`
- `POST /developer/webhooks/deliveries/{deliveryId}/retry`

• Confidence: 80% confidence
• Finding: Webhook management endpoints can alter outbound notification destinations and delivery behavior, which creates security and integrity risks if used without careful review. In a developer automation context, undocumented safeguards around patch/delete operations may lead to accidental disruption, unauthorized exfiltration via attacker-controlled webhook URLs, or weakened event-monitoring integrity.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The capability reference explicitly advertises bulk outbound actions such as approve-all and send-all-approved without any adjacent warning, confirmation requirement, rate-limiting guidance, recipient safeguards, or human-review constraints. In a developer skill, this can normalize high-impact mass email behavior and lead downstream agents or implementers to trigger large outbound sends accidentally, causing spam, compliance, reputational, or operational harm.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: This endpoint map documents numerous destructive and state-changing operations such as delete, cancel, send, approve-all, and key/webhook management without any warning about confirmation requirements, authorization sensitivity, or irreversible effects. In a developer-facing skill, that omission can encourage unsafe automation and accidental misuse of powerful API actions, especially when an agent may translate this reference directly into executable workflows.

Natural-Language Policy Violations

Low

• Confidence: 97% confidence
• Finding: The guardrail says to keep user-facing updates concise and in English unless explicitly requested otherwise. This sets a default language constraint rather than offering a neutral user language choice, which matches the policy's language/locale violation criterion.