pitch-deck
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted user data which is subsequently used to populate a JSON data file and as arguments in command-line operations.\n
- Ingestion points: User-supplied business details gathered during the conversational intake described in SKILL.md Step 1.\n
- Boundary markers: Absent; there are no instructions or delimiters provided to the agent to isolate user-provided content from the operational instructions.\n
- Capability inventory: Local command execution via grep and python3 to process data and generate PowerPoint files.\n
- Sanitization: Absent; the provided scripts and workflow instructions do not include validation or escaping of user-provided strings before they are processed.\n- [COMMAND_EXECUTION]: The skill workflow relies on executing local commands, specifically grep to retrieve reference material from pitch_deck_best_practices.md and python3 to run the generation script scripts/create_pitch_deck.py. While these are used for the skill's primary purpose, they represent a potential execution surface if inputs are not properly handled.\n- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the python-pptx library from the standard Python Package Index (PyPI). This is a well-known and legitimate package necessary for the skill's PowerPoint generation functionality.
Audit Metadata