The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill includes a bundle_analyzer.py script and instructions that lead the agent to process external data (the user's source code and configuration files).
Ingestion points: The scripts/bundle_analyzer.py script reads package.json and scans source files in src/, app/, and pages/ directories (relative to the project root).
Boundary markers: The script and surrounding instructions do not explicitly define boundary markers or 'ignore' instructions for the content of the files being analyzed.
Capability inventory: The script performs file-system read operations and outputs a report to stdout. The agent has the capability to execute this script and interpret its results.
Sanitization: The script does not appear to sanitize the content read from user project files before using it in regex-based analysis or including file paths in the output report.

performance