Security audit

DeckLingo for PPTX

Security checks across malware telemetry and agentic risk

Overview

The skill appears to translate PowerPoint files as advertised, but it can send slide and speaker-note text to Google Translate without a clear consent step, so users should review it before using sensitive decks.

Install only if you are comfortable with editable slide text and optionally speaker notes, layouts, or masters being processed by a Google-backed translation dependency. Avoid using it on confidential, regulated, or customer-sensitive decks unless you first modify it to require explicit external-translation consent, pin dependencies, and confirm where translated text is sent and retained.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection

Findings (8)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 87% confidence
Finding: The skill clearly instructs the agent to invoke local Python scripts that read and write PPTX files and execute shell commands, but it does not declare corresponding permissions. This creates a trust and sandboxing gap: an agent runtime or reviewer may underestimate the skill's actual capabilities, increasing the risk of unintended file access or execution of unreviewed local code.

Description-Behavior Mismatch

Medium

Confidence: 97% confidence
Finding: The code constructs a deep_translator GoogleTranslator and later uses it to translate extracted slide text, which sends presentation content to an external service. Because PPTX files often contain confidential business material, transmitting that content off-host without clear disclosure or consent creates a real data exposure risk, even if the behavior is functionally intended.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill enables implicit invocation without defining any trigger constraints, exclusions, or contextual safeguards. This can cause the agent to auto-select the skill in situations where the user did not clearly intend to process a PowerPoint deck, potentially exposing sensitive slide content to the skill or causing unintended actions in broader workflows.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: At the point where rewrite_pptx is invoked, the script processes user-supplied deck contents and ultimately transmits matched paragraph text to the external translator without any in-code warning, confirmation, or privacy notice. In this skill context, users may reasonably expect a file transformation utility, not external exfiltration of slide and notes text, so the lack of disclosure materially increases privacy and compliance risk.

Unpinned Dependencies

Low

Category: Supply Chain
Content: lxml>=5.0.0 deep-translator>=1.11.4
Confidence: 97% confidence
Finding: lxml>=5.0.0

Unpinned Dependencies

Low

Category: Supply Chain
Content: lxml>=5.0.0 deep-translator>=1.11.4
Confidence: 97% confidence
Finding: deep-translator>=1.11.4

Known Vulnerable Dependency: lxml — 10 advisory(ies): CVE-2021-43818 (lxml's HTML Cleaner allows crafted and SVG embedded scripts to pass through); CVE-2014-3146 (lxml Cross-site Scripting Via Control Characters); CVE-2021-28957 (lxml vulnerable to Cross-Site Scripting ) +7 more

High

Category: Supply Chain
Confidence: 83% confidence
Finding: lxml

Known Vulnerable Dependency: deep-translator — 1 advisory(ies): PYSEC-2022-252 (The deep-translator project on PyPI was taken over via user account compromise v)

High

Category: Supply Chain
Confidence: 95% confidence
Finding: deep-translator

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.