Security audit

Weekly episode feed gate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed podcast feed validation helper that uses a third-party MCP service on public podcast URLs, with supply-chain and remote-service cautions but no evidence of malicious behavior.

Before installing, be aware that the setup command can fetch current third-party code and that checks send public podcast feed or media URLs to PowMCP for live validation. Use pinned or reviewed installation sources in sensitive environments, and avoid submitting private feeds or secret-bearing URLs unless you are comfortable with that service receiving them.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:37
Finding: Unpinned Third-Party Installer and Mutable Skill Source
Content: View full analysis
Remediation: View remediation
add ... ``` 2. Pin `powmcp/skills` to an immutable release tag or, preferably, a verified commit hash. 3. Publish and verify cryptographic integrity hashes or signed release provenance for distributed packages. 4. Use lockfiles where the installation workflow supports them and require reproducible dependency resolution. 5. Document the expected package publisher, source repository, release identifier, and checksum so users can verify authenticity before execution. 6. Avoid automatic execution of newly resolved dependencies. Download and inspect the package first in sensitive environments, or run installation in a restricted sandbox with no secrets and minimal filesystem access. 7. Establish dependency update review procedures so version changes receive security review before documentation is updated. ]]>

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (2)

Rp1

Medium

Category: MCP Rug Pull
Confidence: 92% confidence
Finding: The skill instructs users to run npx skills add powmcp/skills --skill publish-weekly-episode-without-feed-breakage without pinning an exact package version. This allows the fetched package or its transitive dependencies to change over time, creating a supply-chain risk where a compromised or malicious later release could execute code on the user's machine during installation or use.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill enables allow_implicit_invocation without any visible trigger constraints, so the agent may invoke this external MCP tool in broader situations than intended. Because the tool reaches a third-party network endpoint, ambiguous activation increases the chance of unreviewed external requests, unintended data exposure in URLs or prompts, and surprise behavior during ordinary conversations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.