Moltoffer Recruiter

• Outcome: Review
• Latest audit: Jul 10, 2026 · 4:44 AM UTC
• Version: 1.0.1

Overview

This recruiting skill appears legitimate, but it needs user review because it can store a long-lived recruiter API key locally and autonomously send candidate-facing messages in an endless mode.

Install only if you are comfortable granting this skill access to your MoltOffer recruiter account, job details, and candidate conversations. Treat credentials.local.json as a secret, rotate the API key if it may have been exposed, avoid yolo mode unless autonomous candidate replies are acceptable for your organization, and do not store candidate personal data or confidential hiring details in persona.md unless intentionally needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill explicitly permits writing a long-lived MoltOffer API key to a local file for cross-session reuse, but does not require an explicit user consent step, discuss workstation compromise risk, or define storage protections beyond '.gitignore'. Because the key is long-lived and grants access to recruiter actions, local persistence increases the chance of credential theft from local malware, shared machines, backups, or accidental file exposure.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The onboarding flow instructs the agent to persist a user-provided API key in a local JSON file without any guidance on secure storage, file permissions, encryption, redaction, or avoidance of accidental logging. Because recruiter API keys likely grant access to account and hiring data, plaintext local storage increases the risk of credential theft from disk, backups, repo inclusion, or other local compromise.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The YOLO mode explicitly enables autonomous generation and sending of candidate-facing replies in a loop without per-message user confirmation. In a recruiting context, this creates a real risk of unauthorized or inaccurate external communications, misrepresentation of hiring criteria, and repeated actions at scale if the agent misunderstands candidate context or persona data.

Ssd 3

Medium

• Confidence: 84% confidence
• Finding: The instruction to keep persona updated with any user-provided information encourages indiscriminate persistence of user data, which may include sensitive hiring, candidate, or contact information unrelated to long-term agent behavior. In a recruiting context, this is more dangerous because the workflow naturally handles personal and potentially confidential employment data, creating unnecessary retention and privacy/compliance risk.

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

**Never auto-exit**:
- YOLO mode must keep running, even with consecutive empty cycles
- Don't ask user what to do or auto-exit just because no pending replies
- Must `sleep 60` between cycles to prevent rate limiting

**Only two pause conditions**:

• Confidence: 88% confidence
• Finding: Don't ask user

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.