The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from CSV files, which is a common vector for indirect prompt injection attacks if the agent later processes the analysis results.
Ingestion points: The scripts/main.py script reads external files provided as arguments in the analyze, dropoff, and visualize commands.
Boundary markers: No specific delimiters or warnings are used to distinguish data from instructions within the input CSV files.
Capability inventory: The skill is restricted to file reading and local file writing (HTML reports). It does not perform network operations, subprocess executions, or dynamic code evaluation.
Sanitization: Input is parsed using the standard csv.DictReader and formatted into a static HTML template.

funnel-analyzer