Back to skill

Security audit

pet video narration

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed pet-video narration workflow, with no hidden persistence, credential access, or unrelated data handling found.

Before installing, confirm that you are comfortable sending pet videos and generated narration text to whatever video-understanding and text-to-speech tools your agent uses. Also confirm the narration language and voice, since the skill is primarily written for Mandarin narration. Let the agent install ffmpeg only if you trust the environment and need local media merging.

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
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description is written as a Chinese-only activation/use description and frames the skill around Chinese-language narration by default. This can violate language/locale policy when the skill does not explicitly offer opt-in or choice of output language except for a limited English voice mention later.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The recommended voice table assigns Chinese (Mandarin) voices for all listed pet/style categories, with English treated as a special case. This sets a forced locale default rather than presenting language as a user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire reference manual is written in Chinese and provides no indication that language selection is optional or limited to a China-specific use case. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.