Security audit

Podcast Manager

Security checks for vulnerabilities and agentic risk

Overview

This podcast skill is mostly purpose-aligned, but its bundled feed-checking script can be tricked into contacting private or internal network addresses.

Review before installing if the agent will run the bundled feed_probe.py or fetch arbitrary feed URLs from untrusted sources. Use only trusted podcast feed URLs, and prefer a version that revalidates every redirect target or restricts feed fetching to known public podcast hosts.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: scripts/feed_probe.py:38
Finding: SSRF Protection Bypass Through Unvalidated Redirects and DNS Rebinding
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill instructs use of network-capable actions (web_search, web_fetch) but does not declare any explicit tool scope such as permissions or allowed-tools. This creates an authorization ambiguity where a host agent may permit broader tool access than intended, increasing the risk of unintended external requests, data exposure through fetched URLs, or policy bypass via implicit network use.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.