Back to skill

Security audit

Blog Content Processor

Security checks for vulnerabilities and agentic risk

Overview

This skill describes a user-directed RSS/video-to-GIF processor with expected network and file-output behavior, but it should document those risks more clearly.

Install only from a source you trust, pin and review dependencies before running, use feeds and embedded videos you consider trustworthy, and direct output to a controlled folder because media processing can consume CPU and disk space.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill metadata and usage text describe functionality but do not warn users that running the skill will make outbound requests to arbitrary RSS/Atom feed URLs, may follow embedded video links, and will write generated GIF artifacts to disk. This can create privacy, network exposure, storage-consumption, and trust-boundary risks, especially when users assume the skill is a local content transformer rather than a downloader/processor of untrusted remote content.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
94% confidence
Finding

The dependency uses a caret range (^3.12.0), which permits automatic installation of newer minor/patch releases rather than a fully fixed version. This increases supply-chain risk because a compromised or breaking upstream release could be pulled into builds without explicit review, though the package itself is common and nothing else in this file suggests deliberate abuse.

Content

Scanner excerpt · package.json (reported line 10)May include surrounding context.

json
"author": "Content Team",
  "license": "MIT",
  "dependencies": {
    "rss-parser": "^3.12.0",
    "ffmpeg-static": "^5.1.0"
  },
  "clawhub": {

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
95% confidence
Finding

The ffmpeg-static dependency is also specified with a caret range, allowing upstream updates to be fetched automatically. This is somewhat more sensitive than a typical library because it delivers a prebuilt native binary, so an unexpected compromised release could have higher supply-chain impact on systems that install or execute it.

Content

Scanner excerpt · package.json (reported line 11)May include surrounding context.

json
"license": "MIT",
  "dependencies": {
    "rss-parser": "^3.12.0",
    "ffmpeg-static": "^5.1.0"
  },
  "clawhub": {
    "skillType": "content-processor",