Security audit

language-immersion-tv

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent local subtitle-analysis skill, with a caution that CSV exports can carry unsafe spreadsheet formulas from untrusted subtitle text.

Reasonable to install for local subtitle-to-flashcard workflows. Use subtitle files you trust when exporting CSV, or inspect/sanitize CSV output before opening it in Excel, Google Sheets, or similar tools; JSON or Anki TSV output is preferable when handling untrusted subtitles.

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

Warning

Location: scripts/immersion.py:401
Finding: CSV Formula Injection Through Untrusted Subtitle Context
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 (3)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 84% confidence
Finding: The skill documentation instructs users to run commands that read subtitle files and write output decks, but the manifest does not declare any explicit tool scope or permissions. That mismatch weakens reviewability and least-privilege controls: an agent could be granted broader file access than necessary, and consumers cannot easily verify what filesystem operations the skill expects.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This section uses prescriptive language to require a specific language/locale behavior: subtitles must be in the target language, and native-language subtitles are explicitly marked 'Incorrect.' Under the policy, forcing a language choice without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This skill is explicitly multilingual, but the top-level examples and defaults emphasize English usage and include --language en as the recurring example without any natural-language notice that users can choose another supported language. While not a hard restriction, this can be read as privileging a specific language/locale in the skill's user-facing guidance.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.