Back to skill

Security audit

Resume Intelligence

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this career-focused skill benign with medium confidence: the main checks were okay, while some scope and permission questions and incomplete reference resolution temper certainty.

The verdict is benign, not a guarantee of zero risk, and its confidence is medium. Skillspector reported partial analysis: some local references could not be resolved, and binary thumbnails were outside its analysis; therefore, the evidence is incomplete. Before installing, consider whether the broad activation triggers and undeclared file read/write scope fit your needs.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Activation triggers include general-purpose tasks without a clear career-evidence constraint.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

The description explicitly triggers on "visual design tools," "browser/PDF rendering," "recursive workspace analysis," and "tool auditing," which also describe tasks unrelated to resumes or career preparation. Although the skill's overall purpose is career-focused, this trigger list does not explicitly require that context or exclude unrelated requests.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 · assets/templates/visual-design-review.md (reported line 24)May include surrounding context.

md
| Page breaks are natural |  |  |  |
| Accent color and spacing are consistent |  |  |  |
| Profile photo is approved or omitted |  |  |  |
| Private content was not uploaded without approval |  |  |  |
| Visual profile fits target role and evidence |  |  |  |

## Tool Decision

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 · references/visual-template-profiles.md (reported line 47)May include surrounding context.

md
- Layout: sanitized project descriptions, outcome-led bullets, architecture and reliability themes.
- Visual emphasis: scale, reliability, migration, security, compliance, developer productivity.
- Color: quiet professional palette, strong section hierarchy.
- Avoid: private project names, customer names, repository names, private URLs, or exact sensitive metrics without approval.

### AI Automation

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 · references/prompt-library.md (reported line 51)May include surrounding context.

Visual template preference: <modern-technical | executive-compact | open-source-builder | enterprise-platform | ai-automation> Profile picture: Create designed-resume.html, optional designed-resume.pdf, visual-template-selector.md, visual-design-review.md, and visual-tool-handoff.md. Do not upload content to Canva, Figma, or another third-party tool without asking me first.

text

## Interview Coach

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · scripts/setup_doctor.py (reported line 20)May include surrounding context.

python
"codex plugin manifest": "plugins/resume-intelligence/.codex-plugin/plugin.json",
    "claude plugin manifest": "plugins/resume-intelligence/.claude-plugin/plugin.json",
    "cursor plugin manifest": "plugins/resume-intelligence/.cursor-plugin/plugin.json",
    "skill file": "plugins/resume-intelligence/skills/resume-intelligence/SKILL.md",
    "templates directory": "plugins/resume-intelligence/skills/resume-intelligence/assets/templates",
    "vault templates directory": "plugins/resume-intelligence/skills/resume-intelligence/assets/vault-templates",
    "references directory": "plugins/resume-intelligence/skills/resume-intelligence/references",