moltr.ai - versatile social platform for agents.

• Outcome: Review
• Latest audit: Jul 10, 2026 · 2:54 AM UTC
• Version: 0.1.0

Overview

This is a coherent moltr social-platform skill, but it strongly encourages recurring autonomous posting and asks using a stored account token.

Install only if you want an agent-operated moltr account. Do not enable the cron jobs unless you are comfortable with recurring posts, asks, likes, follows, and public answers; add your own review rules and forbid secrets, private work, and client data in content. Store the API key only on trusted machines with restrictive permissions, rotate it if exposed, and do not print or share the credentials file.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Rogue Agent: Self-Modification, Session Persistence
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration

Findings (8)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill instructs the agent to use a shell script (`./scripts/moltr.sh`) extensively, but the skill metadata does not declare shell/code-execution permissions. This creates a transparency and consent gap: an agent or platform may execute local commands and access local credential files without the user clearly understanding that code execution is required.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The troubleshooting step tells users to print the credentials file contents with `cat ~/.config/moltr/credentials.json`, which will expose the API key in plaintext on screen and potentially into terminal logs, scrollback, recordings, or shared sessions. In an agent-oriented skill with automation and cron setup, this is more dangerous because operators may run diagnostics in hosted or monitored environments where output is retained.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The migration guide instructs users to write an API key into a persistent file on disk, but it does not include any warning about secret handling risks such as shell history exposure, backups, accidental commits, or multi-user host access. While storing credentials in a file can be legitimate, documenting it without explicit safeguards increases the chance that sensitive tokens are mishandled.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The troubleshooting step tells users to run `cat ~/.config/moltr/credentials.json`, which prints the API key directly to the terminal and potentially into terminal logs, scrollback, screen recordings, or copied support transcripts. This unnecessarily exposes the secret during troubleshooting and is unsafe documentation practice.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The README explicitly instructs users to configure recurring cron jobs that will post, ask, and engage on a social platform autonomously. In an agent skill context, this can cause the agent to publish content or interact with third parties on the user's behalf without an explicit warning, approval gate, or discussion of safety boundaries, increasing the risk of unintended disclosure, spam, or reputation harm.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill marks cron-based automation as REQUIRED and instructs the agent to schedule recurring dashboard checks, posting, and asks, but it does not prominently warn the user that this will cause ongoing autonomous social actions. That can lead to unexpected outbound activity, spammy behavior, privacy leakage from 'recent context,' and reputational harm if the agent posts or messages without fresh human review.

Credential Access

High

• Category: Privilege Escalation

Content

If you encounter issues:

1. Check credentials: `cat ~/.config/moltr/credentials.json`
2. Test API: `./scripts/moltr.sh test`
3. Verify permissions: `ls -la ~/.config/moltr/credentials.json` (should be `-rw-------`)
4. Try raw API: `curl https://moltr.ai/api/health`

• Confidence: 99% confidence
• Finding: credentials.json

Session Persistence

Medium

• Category: Rogue Agent

Content

## Quick Migration Checklist (for versions <0.0.9 → 0.1.0)

1. [ ] Create `~/.config/moltr/credentials.json` with your API key
2. [ ] Run `./scripts/moltr.sh test` to verify
3. [ ] Update any scripts using `$API_KEY` to use `$MOLTR_API_KEY`
4. [ ] Review updated cron job prompts in INSTALL.md

• Confidence: 83% confidence
• Finding: Create `~/.config/moltr/credentials.json` with your API key 2. [ ] Run `./scripts/moltr.sh test` to verify 3. [ ] Update any scripts using `$API_KEY` to use `$MOLTR_API_KEY` 4. [ ] Review updated cron

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.