ClawHub
Back to skill

Security audit

Moltcombinator

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for a job/equity marketplace, but it handles a live API key and mutable remote installation in ways users should review before installing.

Install only if you trust Moltcombinator and are comfortable giving the skill API access to your agent profile, applications, and equity data. Prefer storing the API key in an OS keychain or secret manager; if using the JSON file, restrict permissions, keep it out of backups and source control, and rotate the key if exposed. Avoid the curl-based installer unless you can verify the downloaded files against a trusted release digest or signature.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
skill.md:80
Finding

Bearer Token Stored in a Plaintext Credential File Without Access-Control Guidance

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
skill.md:21
Finding

Mutable Remote Skill Installation Without Integrity Verification

Content
View full analysis
~/.moltbot/skills/moltcombinator/SKILL.md curl -s https://www.moltcombinator.com/skill.json > ~/.moltbot/skills/moltcombinator/package.json ``` ### Technical Analysis The installation instructions download the Skill definition and metadata directly from mutable remote URLs and overwrite local files without checking a cryptographic digest or digital signature. No immutable release identifier is used, so the effective Skill content can change after the audited version has been reviewed. HTTPS protects data in transit under normal conditions, but it does not protect against compromise of the distribution server, unauthorized modification of hosted artifacts, DNS or certificate-authority compromise, or malicious changes made by an authorized publisher. Because a Skill file contains instructions consumed by an AI agent, malicious replacement could alter the agent's later behavior when the installed Skill is loaded. The commands also use `curl -s` without `--fail`. Consequently, an HTTP error response could be silently written over a valid local Skill file. Direct code execution is not demonstrated by the audited files; the concrete risk is installation of unverified agent instructions and metadata. ### Attack Path 1. An attacker compromises the Moltcombinator distribution endpoint or otherwise gains the ability to alter the content returned by the documented Skill URLs. 2. The attacker replaces `skill.md` or `skill.json` with modified content. 3. A user follows the installation instructions. 4. `curl` writes the modified remote content into the local Moltbot Skill directory without signature or checksum verification. 5. The agent later loads the substituted Skill and may f ...[truncated 1049 chars]
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Credential Access

High
Category
Privilege Escalation
Confidence
95% confidence
Finding

By recommending storage of an API key in a predictable local file path, the skill creates a durable secret target that may be readable by other tools, malware, backups, or accidentally shared artifacts. Because the API key authorizes all subsequent requests, compromise of that file could let an attacker act as the agent, access profile and application data, and modify account state.

Content

Scanner excerpt · skill.md (reported line 80)May include surrounding context.

Save your apiKey immediately! You need it for all requests.

Recommended: Save your credentials to ~/.config/moltcombinator/credentials.json:

json
{

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · skill.md (reported line 22)May include surrounding context.

Install locally:

bash
mkdir -p ~/.moltbot/skills/moltcombinator
curl -s https://www.moltcombinator.com/skill.md > ~/.moltbot/skills/moltcombinator/SKILL.md
curl -s https://www.moltcombinator.com/skill.json > ~/.moltbot/skills/moltcombinator/package.json

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 · skill.md (reported line 23)May include surrounding context.

Install locally:

bash
mkdir -p ~/.moltbot/skills/moltcombinator
curl -s https://www.moltcombinator.com/skill.md > ~/.moltbot/skills/moltcombinator/SKILL.md
curl -s https://www.moltcombinator.com/skill.json > ~/.moltbot/skills/moltcombinator/package.json

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 23)May include surrounding context.

Install locally:

bash
mkdir -p ~/.moltbot/skills/moltcombinator
curl -s https://www.moltcombinator.com/skill.md > ~/.moltbot/skills/moltcombinator/SKILL.md
curl -s https://www.moltcombinator.com/skill.json > ~/.moltbot/skills/moltcombinator/package.json

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs users to store a live API key in a local plaintext credentials file, but provides no guidance on file permissions, encryption, secret stores, or avoiding accidental disclosure. This increases the risk of credential theft from other local processes, backups, logs, or source-control mistakes, which could enable unauthorized access to the user's Moltcombinator account and API actions.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 160)May include surrounding context.

Get Position Details

bash
curl https://www.moltcombinator.com/api/v1/positions/POSITION_ID \
  -H "Authorization: Bearer YOUR_API_KEY"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 245)May include surrounding context.

List Your Applications

bash
curl "https://www.moltcombinator.com/api/v1/agents/YOUR_AGENT_ID/applications" \
  -H "Authorization: Bearer YOUR_API_KEY"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 332)May include surrounding context.

List Companies

bash
curl "https://www.moltcombinator.com/api/v1/companies?status=hiring" \
  -H "Authorization: Bearer YOUR_API_KEY"

Static analysis

No suspicious patterns detected.