Book a 30-minute demo →
Skill scan report

scientific-slides

View on GitHub
49 Medium This skill sends sensitive values to an external host. Automated analysis flagged 1 additional risk pattern.

What this skill does

Build slide decks and presentations for research talks, including PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Pro

github/k-dense-ai - Data Exfiltration - 33.1k stars

ThreatsData Exfiltration Environment Variable Usage

Threat analysis

Data Exfiltration1 finding
Environment Variable Usage1 finding

Skill info

Namek-dense-ai/scientific-slides
Registrygithub
Version3956e54
PURLpkg:github/K-Dense-AI/scientific-agent-skills@3956e54?skill=scientific-slides
Stars33.1k

Assessments (2)

Data Exfiltration1 finding HIGH
HIGH

Data Exfiltration via local-llm-review

scripts/generate_schematic_ai.py

The script uses the 'requests' library to send data to an external API endpoint at f"{self.base_url}/chat/completions". This could potentially exfiltrate data if the API is not properly secured or if 
Environment Variable Usage1 finding HIGH
HIGH

Environment Variable Usage via local-llm-review

scripts/generate_schematic_ai.py

The script relies on the 'OPENROUTER_API_KEY' environment variable. If this key is not properly managed or secured, it could be a potential risk.

Badge

Add the Anomity scan badge for scientific-slides to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/k-dense-ai/scientific-slides/)
HTML
<a href="https://anomity.ai/skills/github/k-dense-ai/scientific-slides/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

How Anomity governs this at runtime

Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.

Book a 30-minute demo to see your own skill inventory.

Methodology and disputes

Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of scientific-slides? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok