math-presentation-beamer

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided talk content (topic, audience, duration, and figures) to generate LaTeX source code and speaker notes.
  • Ingestion points: The skill takes 'talk content' and 'figures' as input in SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious instructions potentially embedded in the user-provided presentation content.
  • Capability inventory: The skill involves writing .tex, .sty, and markdown files, and includes a step for compiling the LaTeX source.
  • Sanitization: No sanitization or validation logic is specified for the external talk content before it is processed into the presentation structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 02:59 AM
Security Audit — agent-trust-hub — math-presentation-beamer