ClawHub
Back to skill

Security audit

mysteries-finalize

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent video-project finalization workflow, with expected local file processing and external translation use that users should be aware of.

Install only if you want an agent to process files inside a Farsight project's Renders/Final/ folder, generate derivative transcript/subtitle/thumbnail files, and use an external translation library for localized subtitles. Confirm the target project folder before running because the trigger wording is broader than the safest possible phrasing.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger language is broad enough that normal user requests like 'finalize a project' or 'prepare final assets' could invoke this skill unexpectedly. Because the skill performs file operations and launches external tools, overbroad activation increases the chance of unintended execution on the wrong workspace or project data.

Content

No source excerpt is available for this finding.

Unbounded Output

Medium
Category
Output Handling
Confidence
75% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md
- **Base HD:** 1920x1080, optimized to < 3MB.
   - **BIG:** 3840x2160, optimized to < 2MB.
   - **social_media:** 1200x630, optimized to 200KB - 300KB.
   - **Featured:** 3840x1440, no size limit, high quality. (Use Original Crop Rule)
   - **Featured_v2:** 3840x1440, no size limit, high quality. (Use Uncropped Seamless Fill Rule)
   - **email:** 650x366, optimized to < 100KB.

Unbounded Output

Medium
Category
Output Handling
Confidence
75% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

md
- **Base HD:** 1920x1080, optimized to < 3MB.
   - **BIG:** 3840x2160, optimized to < 2MB.
   - **social_media:** 1200x630, optimized to 200KB - 300KB.
   - **Featured:** 3840x1440, no size limit, high quality. (Use Original Crop Rule)
   - **Featured_v2:** 3840x1440, no size limit, high quality. (Use Uncropped Seamless Fill Rule)
   - **email:** 650x366, optimized to < 100KB.