Slides

• Analyzed: May 12, 2026, 4:16 AM
• Findings: 1
• Version: 1.0.0
• Hash: ddacbeaea5b5221caaff975475e72d47dde616cec01e4dd4064b98a0598f51ac
• Source: palm
• External report: View on VirusTotal

Findings (1)

The skill is classified as suspicious due to its inherent capabilities that introduce a significant attack surface, primarily the ability to execute shell commands (e.g., `npm install`, `npx`, `marp`, `decktape` as described in `tools.md`, and `mkdir -p` in `SKILL.md` and `memory-template.md`). This capability, while necessary for the skill's stated purpose of using programmatic tools, poses a risk for potential shell injection vulnerabilities if agent input is not rigorously sanitized. Additionally, the skill describes handling sensitive API credentials (`creds.json`) for the Google Slides API in `tools.md`, which, despite being a standard authentication method, represents a sensitive operation. While the `SKILL.md` includes strong 'NEVER' rules against unauthorized actions, the underlying capabilities warrant a 'suspicious' classification rather than 'benign' due to the potential for exploitation.