ClawHub
Back to skill

Security audit

plydb

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PlyDB helper for querying user-configured databases and files, with no packaged executable code or hidden behavior found.

Install only if you intend to let an agent use PlyDB against configured data sources. Review configs carefully, prefer least-privilege database and cloud credentials, and be aware that Google Sheets OAuth may cache authorization for later PlyDB calls.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes very generic terms such as "sql", "query", "csv", "excel", and "database", which can cause the skill to activate in many contexts beyond explicit PlyDB use. In an agent environment, unintended activation can route unrelated user requests into a tool-capable skill that works with local files and connected data sources, increasing the chance of unnecessary data access or execution of risky data queries.

Content

No source excerpt is available for this finding.

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · references/config_schema.md (reported line 102)May include surrounding context.

md
This is equivalent to supplying `--semantic-context-overlay` on the CLI, but
embedded in the config file.

| Field      | Type             | Description                                                                                                                                                                  |
| ---------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `overlays` | Array of Strings | Ordered list of paths to [Open Semantic Interchange (OSI)](https://github.com/open-semantic-interchange/OSI) YAML files. Applied after auto-scan semantic context, in order. |

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file documents that if no credential profile is provided, browser-based OAuth and an interactive Google login flow will be used. Because this behavior can transmit user data to an external service and trigger authentication outside the local system, the description should include a clear user-facing warning about that effect.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.