create-lecture

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection due to its core workflow of processing untrusted data.
  • Ingestion points: In Phase 0 and Phase 1, the agent is instructed to read "Any source papers / existing slides the user provided" and "extract key ideas".
  • Boundary markers: The instructions lack delimiters or specific warnings to ignore system-like instructions that may be contained within the source papers or PDFs.
  • Capability inventory: The skill allows the use of Bash, Task, Write, and Edit tools, which could be leveraged to perform unauthorized actions if an injection is successful.
  • Sanitization: There is no mention of sanitizing, filtering, or validating the content extracted from external documents before it is used to influence the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 07:11 AM
Security Audit — agent-trust-hub — create-lecture