study-notes-creator

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted external data which could contain malicious instructions designed to influence agent behavior.
  • Ingestion points: Processes source materials including PDFs, lecture notes, and documentation provided by the user (SKILL.md).
  • Boundary markers: The instructions lack defined delimiters or specific warnings to ignore embedded instructions within the processed source materials.
  • Capability inventory: The agent is instructed to create directory structures, write multiple markdown files, and generate complex Mermaid diagrams based on the content of the ingested files.
  • Sanitization: There are no specified sanitization, filtering, or validation steps for the external content before it is processed and interpolated into the note-creation workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 09:57 AM
Security Audit — agent-trust-hub — study-notes-creator