academic-beamer-deck

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and transform untrusted data from the user.
  • Ingestion points: According to the description in SKILL.md, the skill accepts user-provided .tex files, figures, and presentation context.
  • Boundary markers: The instructions do not provide explicit delimiters or guidance for the agent to distinguish between user-supplied content and the skill's operational instructions.
  • Capability inventory: The skill lacks dangerous capabilities such as direct network access, arbitrary shell execution, or file system manipulation beyond document generation (SKILL.md).
  • Sanitization: No sanitization, escaping, or validation logic is specified for the content extracted from user-supplied materials before it is incorporated into the generated LaTeX code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 12:30 PM