The Agent Skills Directory

[COMMAND_EXECUTION] (MEDIUM): The skill instructions in SKILL.md direct the agent to execute shell commands, specifically python3 scripts/create_pitch_deck.py. Since the content of this script is not included in the skill package for analysis, its behavior and safety cannot be verified.
[EXTERNAL_DOWNLOADS] (LOW): The troubleshooting section suggests the manual installation of the python-pptx library using pip3. While a common library, this introduces a dependency on external, unversioned code.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill possesses a surface for indirect prompt injection.
Ingestion points: User-provided company information, problem statements, and business details are gathered in 'Step 1' and written to pitch_data.json in 'Step 3'.
Boundary markers: Instructions for creating pitch_data.json lack explicit boundary markers or instructions to ignore embedded commands within the user data.
Capability inventory: The skill executes a subprocess via python3 to process the generated JSON data.
Sanitization: No sanitization or validation logic is defined for the user-provided strings before they are incorporated into the JSON file or processed by the script.

pitch-deck