consulting-deck
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions provide guidance for the agent to set up a local execution environment, including creating a Python virtual environment and installing the engine from the skill's source directory using
pip. This is standard for local tool integration. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data from user-provided files such as research notes, specifications, and existing slide decks. The instructions include clear security boundaries, directing the agent to treat all such content as data rather than instructions and explicitly warning against the execution of commands or macros found within those files.
- [EXTERNAL_DOWNLOADS]: The documentation provides standard instructions for installing the skill and its dependencies from the developer's GitHub repository (
BotTony329/consulting-deck-skill), which is consistent with the skill's intended deployment model.
Audit Metadata