Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security

Agent skills let LLM agents reuse instructions, resources, tools, and workflows, but they also create a new place for malicious behavior to hide. A skill may look benign in its documentation or code while becoming harmful only when it is invoked with particular user requests, local assets,...

EUVD-2021-31643

Malicious code in bioql PyPI...

CVE-2021-44840

An issue was discovered in Delta RM 1.2. Using an privileged account, it is possible to edit, create, and delete risk labels, such as Criticality and Priority Indication labels. By using the /core/table/query endpoint, and by using a POST request and indicating the affected label with tableUid...

CVE-2021-44840

An issue was discovered in Delta RM 1.2. Using an privileged account, it is possible to edit, create, and delete risk labels, such as Criticality and Priority Indication labels. By using the /core/table/query endpoint, and by using a POST request and indicating the affected label with tableUid...

Design/Logic Flaw

An issue was discovered in Delta RM 1.2. Using an privileged account, it is possible to edit, create, and delete risk labels, such as Criticality and Priority Indication labels. By using the /core/table/query endpoint, and by using a POST request and indicating the affected label with tableUid...

CVE-2021-44840

Delta RM 1.2 contains a vulnerability where a privileged user can edit, create, and delete the following risk labels (Priority Indication, Quality Evaluation, Progress Margin, Priority) via the /core/table/query endpoint using a POST request with the affected label identified by tableUid and the ...