presentation

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it ingests untrusted user data and interpolates it into a generated HTML file.
  • Ingestion points: In SKILL.md, Step 2 instructs the agent to gather source material such as documents, outlines, notes, and "brain dumps" from the user.
  • Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to ignore potentially malicious commands embedded within the user's content.
  • Capability inventory: The skill's core capability is generating a standalone HTML file containing embedded CSS and a JavaScript navigation engine (framework-reference.md).
  • Sanitization: There are no instructions for the agent to sanitize or escape user-provided text before inserting it into the HTML templates, creating a risk that malicious scripts could be included in the final exported presentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 11:04 PM
Security Audit — agent-trust-hub — presentation