The authors compiled a dataset of 1,248 GitHub Agentic Workflow Markdown files from 276 public repositories.
Developers write detailed, evolving instructions for agentic workflows but often skip safety measures
An empirical study of 1,248 GitHub Agentic Workflow files reveals extensive natural-language instructions, sustained maintenance, and sparse prompt-injection defenses
Academic
Jasem Khelifi · Issam Oukhay · Ali Ouni · Mohammed Sayagh · Mohamed Aymen Saied
École de technologie supérieure (ÉTS) · Université Laval
Research Digest··2 min read
The authors analyzed 1,248 Markdown-based GitHub Agentic Workflow files across 276 repositories.
Why this paper
From École de technologie supérieure (ÉTS) and Université Laval · Part of Agent Security & Attacks, now 45 papers
In one line
GitHub agentic workflows are long, evolving operational specifications, yet explicit prompt-injection defenses appear in only 9.4% of labeled workflows.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§