ClawHub
Back to skill

Security audit

Hardcover.app skill for tracking books you're reading, reading goal, and finding books you'd love to read

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only Hardcover API helper that uses a user-provided token to query book and reading-library data from Hardcover.

Install this only if you want Codex to use your Hardcover API token and send relevant book or reading-library queries to Hardcover. For generic book questions where you do not want Hardcover involved, ask the agent not to use the Hardcover skill or invoke another source explicitly.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger description is broad enough to activate on generic book-related requests such as reading lists, book progress, author or series searches, and syncing reading data. Over-broad routing can cause the agent to invoke this skill in contexts the user did not intend, leading to unnecessary access to private Hardcover data or transmission of user queries to an external service.

Content

No source excerpt is available for this finding.

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 22)May include surrounding context.

md
## Configuration

- **Env variable:** `HARDCOVER_API_TOKEN` from https://hardcover.app/settings
- **Endpoint:** `https://api.hardcover.app/v1/graphql`
- **Rate limit:** 60 req/min, 30s timeout, max 3 query depth

## Authentication

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 30)May include surrounding context.

md
## Configuration

- **Env variable:** `HARDCOVER_API_TOKEN` from https://hardcover.app/settings
- **Endpoint:** `https://api.hardcover.app/v1/graphql`
- **Rate limit:** 60 req/min, 30s timeout, max 3 query depth

## Authentication

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 30)May include surrounding context.

All queries require Authorization: Bearer {token} header (token from settings, add Bearer prefix):

bash
curl -X POST https://api.hardcover.app/v1/graphql \
  -H "Authorization: Bearer $HARDCOVER_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"query": "query { me { id username } }"}'

Static analysis

No suspicious patterns detected.