ClawHub
Back to skill

Security audit

Jamdesk Docs

Security checks for vulnerabilities and agentic risk

Overview

This skill guides an agent through updating Jamdesk documentation with user confirmation and verification, with no hidden code or persistence beyond a disclosed project config file.

Before installing, be aware that this skill may activate on broad documentation requests and can edit a configured external Jamdesk docs repository. Review the proposed scope, branch choice, diff, and any commit or push prompt before approving changes.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest description includes broad trigger phrases such as 'update docs', 'write docs', and 'document this', which can match many ordinary user requests and cause the skill to activate too eagerly. In this skill's context, over-broad activation is risky because the skill can propose or initiate changes in an external documentation repository and even suggest itself proactively after feature work, expanding its operational scope without strong user intent.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
|--------|-------|
| Include frontmatter (`title` ≤ 60 chars, `description` 120-160 chars) | Create stub pages with "TODO" |
| Use built-in components first | Use `mint.json` (use `docs.json`) |
| Ask clarifying questions before writing | Skip verification |
| State prerequisites up front | Include secrets, tokens, or real customer data |
| Use active voice and action-oriented headings | Promise guarantees ("always works", "instant") |
| Include explicit warnings for destructive steps | Use "click here" link text |

Static analysis

No suspicious patterns detected.