Oathe Security Badge

Is LBCplus/ai-literacy-pedagogy safe?

https://github.com/LBCplus/ai-literacy-pedagogy

98
SAFE

This skill implements a pedagogical methodology called 'Sand to Smart' for teaching AI and civic literacy to underserved populations. The skill contains only educational content with no executable code or security risks detected. While it does include behavioral modification instructions, these are transparent and designed to improve accessibility rather than manipulate users maliciously.

Category Scores

Prompt Injection 95/100 · 30%
Data Exfiltration 100/100 · 25%
Code Execution 100/100 · 20%
Clone Behavior 100/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 90/100 · 5%

Findings (2)

INFO Educational behavioral modification instructions -5

The skill contains specific instructions for how the AI should explain concepts, including rules like 'never start with a definition' and teaching frameworks. However, these are transparent pedagogical instructions designed to improve accessibility for underserved populations.

INFO Civic literacy nonpartisan constraints -10

The skill includes strict nonpartisan rules for civic content that constrain AI responses. While these are positive ethical constraints, they do modify default AI behavior.