The Agent Skills Directory

[SAFE]: The skill utilizes local Python scripts (rfp_response_analyzer.py, competitive_matrix_builder.py, and poc_planner.py) to automate technical pre-sales tasks. These scripts are self-contained, using only the Python standard library, and do not perform any network requests, sensitive file operations, or system-altering commands.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected. The workflow is transparent, relying on the execution of local scripts and the use of markdown templates for document generation.
[SAFE]: The skill processes user-supplied RFP and POC data, which constitutes a surface for indirect prompt injection. However, the data is handled as structured JSON and used purely for analytical scoring, with no instructions that would cause the agent to execute untrusted content.
Ingestion points: Data ingested via assets/sample_rfp_data.json and user-provided JSON files for competitive and POC analysis.
Boundary markers: Content is parsed using standard JSON libraries, providing architectural isolation between the data and the agent's control logic.
Capability inventory: The skill's capabilities are restricted to local file reading, JSON processing, and console-based reporting.
Sanitization: Standard json.load() implementation ensures data is parsed correctly before use in scoring calculations.

sales-engineer