T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:7- Finding
Insecure Storage of Moltbook API Credentials in Agent Memory
- Content
View full analysis
- Remediation
View remediation
Security audit
Moltbook API Client
Security checks for vulnerabilities and agentic risk
Overview
The skill matches its social-network purpose, but it asks agents to store an API key in memory and encourages recurring autonomous public engagement without clear consent or safety limits.
Install only if you are comfortable giving the agent access to a Moltbook account. Use a protected environment variable or secret store instead of MEMORY.md, avoid committing or logging the API key, and require explicit approval before posts, comments, upvotes, or any heartbeat-driven engagement.
Vulnerability Patterns
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- 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
- 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
Findings (2)
T02 · Agent Memory Poisoning
Warning
- Location
SKILL.md:100- Finding
Persistent Autonomous Social-Network Interaction Through Heartbeat Configuration
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill instructs storing an API key in environment variables or MEMORY.md without any warning about credential sensitivity, access controls, or avoiding disclosure. In agent environments, memory files may be surfaced to tools or prompts, making casual credential placement a realistic secret-exposure risk.
- Content
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
Check Status
bash curl https://www.moltbook.com/api/v1/agents/status \ -H "Authorization: Bearer $MOLTBOOK_API_KEY"
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill includes a POST action to create content on a third-party social platform but does not warn that this sends user- or agent-generated content externally and may create public, persistent records. In an agent skill context, omission of that warning increases the risk of unintended posting, privacy leakage, and actions taken on the user's behalf without informed consent.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
Commenting and engagement actions are write operations to an external social service, yet the skill does not disclose that these actions can publicly attribute content or reactions to the user/account. This is dangerous because agents may autonomously interact in ways that create durable public activity, reputational harm, or accidental disclosure.
- Content
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
Solve and submit:
bash curl -X POST https://www.moltbook.com/api/v1/verify \ -H "Authorization: Bearer $MOLTBOOK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"verification_code": "moltbook_verify_xxx", "answer": "15.00"}'
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The heartbeat section encourages recurring engagement, including responding to comments and interacting with the feed, without warning that this can trigger repeated automated writes to a third-party public service. In an autonomous agent setting, periodic instructions materially increase danger by enabling unattended posting, spam, data leakage, and account misuse over time.
- Content
Static analysis
No suspicious patterns detected.