The Agent Skills Directory

[SAFE]: The skill is a self-contained utility that processes a local JSON dataset (data/vc_funds.json) using standard Python libraries. No network activity, data exfiltration, or remote code execution was detected.
[COMMAND_EXECUTION]: The skill relies on local script execution via python scripts/run.py to perform its primary function of matching and report generation.
[PROMPT_INJECTION]: The skill processes untrusted user input (product descriptions and URLs) which are interpolated into a generated report. This constitutes a surface for indirect prompt injection.
Ingestion points: The scripts/run.py script ingests user-provided text via the --description and --url command-line arguments.
Boundary markers: The script does not utilize specific boundary delimiters to isolate user-provided content from the report instructions within the output file.
Capability inventory: The skill has the capability to create directories and write files to the local filesystem using the os and open modules in scripts/run.py.
Sanitization: The scripts/generate_report.py script performs basic sanitization by escaping markdown brackets ([ and ]) in the product description to prevent formatting issues.

vc-curated-match