Back to skill

Security audit

Pain to MVP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent product-research helper that stores public-discussion evidence, opportunities, and PRDs in the user's TiDB database as disclosed.

Install only with a TiDB database you intend this skill to write to, and avoid collecting or saving private, sensitive, or non-public user content unless you want it persisted there. Review retention and access controls on that database because the skill stores evidence snippets, source URLs, author handles, opportunities, and PRD drafts.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · references/contracts.md (reported line 274)May include surrounding context.

md
- Prefer a thin vertical slice.
- Include non-goals, constraints, and acceptance criteria.

## Output Rules

- Prefer repeated, concrete complaints over clever one-offs.
- Separate category pain from vendor-specific complaints.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description is broad enough to match generic product-advice or ideation requests, which can cause unintended activation outside the user's expected workflow. In this skill's context, overbroad invocation is more concerning because the skill can trigger web collection and database persistence, increasing the chance of unnecessary external data handling and side effects from an imprecise match.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description does not warn users that it may collect external discussion content and persist evidence, opportunities, and PRDs to a database via TIDB_DATABASE_URL-backed helper commands. This lack of transparency can lead to users providing prompts under the assumption of ephemeral analysis, creating consent, privacy, and data-governance risks when content is stored or later retrieved.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
93% confidence
Finding

The dependency uses a caret range (^0.3.0), which allows automatic installation of newer compatible releases within the 0.x line. This creates supply-chain risk because builds are not fully reproducible and a compromised or breaking upstream release could be pulled in without explicit review. In this skill, the package is a serverless database client, so compromise could affect data access or introduce malicious code during execution, though this file alone does not show direct exploitation.

Content

Scanner excerpt · package.json (reported line 11)May include surrounding context.

json
"tidb": "node scripts/tidb_tool.mjs"
  },
  "dependencies": {
    "@tidbcloud/serverless": "^0.3.0"
  }
}