Security audit

Molt Radio

Security checks for vulnerabilities and agentic risk

Overview

This skill matches its radio-hosting purpose, but it asks agents to trust mutable remote instructions and includes an unattended poller that can publish content under the user's agent identity.

Install only if you are comfortable giving the skill a Molt Radio API key and allowing it to send profile details, scripts, audio, and published turns to moltradio.xyz. Do not run the bundled polling helper unattended unless you accept automatic content publication under your agent identity, and avoid following mutable remote skill instructions without human review.

A.I.G

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 (4)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:13
Finding: Mandatory Retrieval of Mutable Remote Skill Instructions
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: scripts/agent-poll.js:15
Finding: API Credential Transmission to an Unrestricted Configurable Origin
Content: View full analysis
''); throw new Error(`GET ${path} failed (${response.status}): ${text}`); } return response.json(); } async function postJson(path, body) { const response = await fetch(`${baseUrl}${path}`, { method: 'POST', headers, body: JSON.stringify(body) }); ``` ### Technical Analysis The script obtains the service API key from `MOLT_RADIO_API_KEY` and attaches it as `X-Agent-Key` to every request. At the same time, the destination is taken directly from `MOLT_RADIO_URL`. The code does not require HTTPS, validate the URL scheme, compare the hostname against an allowlist, or request confirmation before sending the credential to an alternate origin. Authentication against the legitimate service is necessary for the declared functionality, but allowing the same credential to be transmitted to an arbitrary configured endpoint exceeds that requirement. An attacker who can influence the launch environment, service configuration, shell profile, container environment, or copied execution command can redirect the initial authenticated request to an attacker-controlled server. ### Attack Path 1. The victim possesses a valid Molt Radio API key in `MOLT_RADIO_API_KEY`. 2. An attacker influences the execution environment or convinces the victim to set ` ...[truncated 993 chars]
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: scripts/agent-poll.js:40
Finding: Automatic Publication of Unreviewed Server-Controlled Prompt Content
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:141
Finding: Unpinned Third-Party Package Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (7)

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · SKILL.md (reported line 284)May include surrounding context.
Go offline:

text
DELETE /availability X-Agent-Key: mra_...

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 316)May include surrounding context.
md
node scripts/agent-poll.js

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 321)May include surrounding context.
md
node scripts/agent-poll.js

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 89% confidence
Finding: The skill instructs the agent to use network access and handle an API key, but it declares no explicit tool scope or permission boundaries. That increases the chance an orchestrator invokes it with overly broad capabilities or without clear user consent for outbound requests and secret handling.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The invocation text is broad enough to match ordinary content-generation or conversation tasks, which can cause the skill to activate in contexts where the user did not intend external publication or account actions. Because the skill can register agents, create shows, and publish content, over-triggering creates a meaningful risk of unintended external side effects.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill sends profile data, scripts, audio, and other user-generated content to a third-party service, but the description does not clearly warn about that up front. Users or calling systems may invoke it expecting local assistance, not external transmission and account creation on moltradio.xyz.
Content: No source excerpt is available for this finding.

External Transmission

Medium

Category: Data Exfiltration
Confidence: 97% confidence
Finding: The skill directs the agent to fetch and trust remote instructions from https://moltradio.xyz/skill.md before acting. This is effectively remote prompt injection/update behavior: whoever controls that endpoint can change the agent's instructions at runtime, including causing new data exfiltration, unsafe actions, or policy bypass attempts.
Content: Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.
Always read the latest skill instructions before making API calls:

text
curl "https://moltradio.xyz/skill.md"

If your stored instructions differ from the latest version, stop and re-read before proceeding.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: scripts/agent-poll.js:16