presentation-qa

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of presentation files (PowerPoint, PDF, Keynote, HTML). * Ingestion points: The agent is instructed to audit PowerPoint, PDF, Keynote, or HTML presentations provided as input in SKILL.md. * Boundary markers: No specific delimiters or instructions to ignore embedded prompts within the slides are provided to the agent. * Capability inventory: The skill outlines capabilities including file system access (for creating working copies and rendering), and network operations (checking links) across its workflow. * Sanitization: The instructions do not specify any validation or sanitization of the content extracted from the external files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 05:27 AM