The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data.
Ingestion points: The skill reads untrusted data from references/ and input/ directories, such as transcripts and blog posts (e.g., references/transcripts/webinar.txt).
Boundary markers: There are no instructions for the agent to use delimiters or ignore embedded instructions within the processed content.
Capability inventory: The skill utilizes the Bash tool to execute several Python scripts (audit_content.py, analyze_repurpose.py, repurpose_content.py) to process the data.
Sanitization: There is no evidence of sanitization or filtering of the external content before it is processed by the scripts.
[COMMAND_EXECUTION]: The skill requires the execution of local Python scripts to perform its primary functions.
Evidence: The documentation provides specific commands to run scripts located in scripts/content/ and scripts/samples/ using the local virtual environment's Python executable (.venv\Scripts\python.exe).

content-repurposer