ClawAudit verdict
adaptive-learning
The skill creates adaptive learning flashcard apps from course materials using FSRS and Bayesian Knowledge Tracing. The code is transparent, well-documented, and does not contain any malicious or deceptive behavior.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (1)
<script> tag in markdown โ potential code injection
scripts/generate-course.sh ยท prose ยท downgraded ยท <script
Permissions & capabilities
No declared permissions โ minimal attack surface.
Is this flag fair?
Thanks โ recorded.