hermesoffice-decks

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill instructs the agent to use execute_slide_script for handling complex, multi-element layout changes. This tool enables the generation and execution of scripts at runtime based on real-time slide geometry and content.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from untrusted sources, including user briefs and web_search results used for charts. This data is then used to populate slide elements and may influence the logic of generated layout scripts.
  • Ingestion points: The skill processes user-provided content for slide planning and external data retrieved via the web_search tool (SKILL.md).
  • Boundary markers: There are no instructions specifying the use of delimiters or warnings to ignore embedded instructions within the processed data.
  • Capability inventory: The skill utilizes execute_slide_script for dynamic execution, web_search for data retrieval, and various set_element tools for content injection.
  • Sanitization: The instructions do not define any sanitization, validation, or escaping procedures for external content before it is processed or interpolated.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 01:24 PM