T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:406- Finding
Arbitrary User Content Is Transmitted to a Third-Party Service
- Content
View full analysis
- Remediation
View remediation
Security audit
Data Format Encoder
Security checks for vulnerabilities and agentic risk
Overview
This skill appears to be an advertised remote text encoder, but it needs review because it can send arbitrary user text to AgentPMT and lets mutable remote/setup content influence behavior.
Install only if you are comfortable sending the text you encode or decode to AgentPMT and spending the listed credits. Do not use it for secrets, credentials, private keys, proprietary files, regulated data, or sensitive payloads unless your organization explicitly approves the AgentPMT service. Prefer local encoding tools for routine transformations, and audit or pin the referenced setup skills before using the npx installation path.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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 (3)
T08 · Insecure Dependencies
Warning
- Location
SKILL.md:388- Finding
Unpinned Third-Party Skill Installation Creates a Supply-Chain Risk
- Content
View full analysis
- Remediation
View remediation
T01 · Skill Instruction Hijacking
Warning
- Location
SKILL.md:319- Finding
Remote Instructions Are Allowed to Override Audited Local Guidance
- 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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (12)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The activation keywords include very broad terms such as
text, which can cause this remote-tool skill to be selected in many unrelated contexts. Because the tool sends user-provided content to an external AgentPMT service, overbroad triggering increases the chance of unnecessary data exposure, unintended paid calls, or workflow confusion in contexts where a local transformation would have been safer.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 89% confidence
- Finding
The skill explicitly routes input to an external MCP/API endpoint at
api.agentpmt.com, meaning any text provided to this encoder may leave the local environment. In context, this tool handles arbitrary user text and even mentions file content and payload encoding use cases, so accidental transmission of secrets, source code, credentials, or regulated data is a realistic confidentiality risk.- Content
md - What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`) - AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`) - Marketplace product: https://www.agentpmt.com/marketplace/data-format-encoder - AgentPMT main MCP server: https://api.agentpmt.com/mcp/ - AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 89% confidence
- Finding
This REST invoke endpoint confirms that tool usage results in external transmission to a third-party service. For an encoding utility, many operations could be performed locally, so the remote design materially increases privacy and compliance risk if agents use it on confidential text without clear consent or data classification checks.
- Content
md - AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`) - Marketplace product: https://www.agentpmt.com/marketplace/data-format-encoder - AgentPMT main MCP server: https://api.agentpmt.com/mcp/ - AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase
Autonomous Decision Making
Medium
- Category
- Excessive Agency
- Confidence
- 80% 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
md Price: `5` credits Convert a hexadecimal string back to plain text. Spaces, colons, and hyphens between hex bytes are automatically removed. Parameters:
Autonomous Decision Making
Medium
- Category
- Excessive Agency
- Confidence
- 80% 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
md Price: `5` credits Convert a hexadecimal string back to plain text. Spaces, colons, and hyphens between hex bytes are automatically removed. Parameters:
Autonomous Decision Making
Medium
- Category
- Excessive Agency
- Confidence
- 80% 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
md Price: `5` credits Convert a hexadecimal string back to plain text. Spaces, colons, and hyphens between hex bytes are automatically removed. Parameters:
Static analysis
No suspicious patterns detected.