deck-refresh

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill is designed to ingest and process data from external sources such as Excel spreadsheets and existing PowerPoint presentations. This introduces a potential surface for indirect prompt injection, where malicious instructions could be embedded within the source data to influence the agent's behavior.
  • Ingestion points: Data is retrieved from uploaded Excel files and existing presentation slides in Phases 1 and 2.
  • Boundary markers: The skill mitigates risk by implementing a strict approval gate in Phase 3, requiring the user to explicitly review and authorize all changes before execution.
  • Capability inventory: The agent can modify live presentation elements or regenerate presentation files with updated values.
  • Sanitization: The instructions do not specify any sanitization or filtering logic for content extracted from external documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:26 PM
Security Audit — agent-trust-hub — deck-refresh