No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by run-llama · Agent Tool · ★ 74
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is llamaparse-agent-skills safe to install? View the security audit →
LlamaParse Skills Unblock document intelligence for your agents with LlamaParse skills. Available Skills llamaparse Skill for unstructured documents parsing and text-extraction leveraging LlamaParse. Use with: PDFs, presentations, Word documents, spreadsheets, images Complex documents which need advanced parsing capabilties in order to get their content extracted Documents with images, charts and tables In general, whenever the agent needs to have access to a deeper layer than just raw text extraction Pre-requisites A available within the environment Node 18+ and (or another package manager) (Optional) typescript package installed in the current Node environment liteparse Skill for local-first, fast document parsing, conversion and spatial text extraction.
| Stars | 74 |
| Forks | 10 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 55.1846741257103/100 |
| Last Updated | 2026-07-03 |
| Created | 2026-03-02 |
| Platforms | python |
| Est. Tokens | ~4k |
These tools work well together with llamaparse-agent-skills for enhanced workflows:
Explore other popular agent tool tools:
llamaparse-agent-skills is LlamaParse Agent Skills. It is categorized as a Agent Tool with 74 GitHub stars.
llamaparse-agent-skills is primarily written in Python.
You can find installation instructions and usage details in the llamaparse-agent-skills GitHub repository at github.com/run-llama/llamaparse-agent-skills. The project has 74 stars and 10 forks, indicating an active community.
llamaparse-agent-skills is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: