The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data files including sales pipelines and financial metrics. While this is the intended primary purpose, it creates a surface where untrusted data is ingested into the agent's context. * Ingestion points: scripts/pipeline_analyzer.py, scripts/forecast_accuracy_tracker.py, and scripts/gtm_efficiency_calculator.py ingest user-supplied JSON data. * Boundary markers: The skill uses defined JSON schemas for input data, providing structural validation. * Capability inventory: The tools are limited to local data processing and report generation with no network access or administrative privileges. * Sanitization: Input is constrained by the expected JSON structure defined in the documentation.
[SAFE]: The skill follows standard development practices for data analysis tools and does not contain hardcoded credentials, obfuscated code, or attempts to persist access or escalate privileges.

revenue-operations