study-explainer

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and explain external, user-provided materials (PDFs, slide decks, transcripts, and images). This creates a surface for indirect prompt injection, where malicious instructions hidden in the study documents could attempt to hijack the agent's logic or output.
  • Ingestion points: Defined in SKILL.md, the skill processes slide decks, PDF notes, transcripts, and images.
  • Boundary markers: The prompt does not specify delimiters or security instructions to separate the untrusted input from the agent's core instructions.
  • Capability inventory: The skill allows the agent to conduct web searches for additional context (SKILL.md, Core Behavior section).
  • Sanitization: There is no evidence of sanitization, filtering, or validation for the content being processed.
  • [NO_CODE]: This skill consists purely of markdown instructions and YAML configuration. No executable code, shell scripts, or external package dependencies were found in the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 12:08 PM
Security Audit — agent-trust-hub — study-explainer