The Agent Skills Directory

[SAFE]: No security vulnerabilities, malicious patterns, or unintended behaviors were found during the analysis of the skill's instructions, references, or code.
[COMMAND_EXECUTION]: The skill includes Python scripts (partner_tier_classifier.py, joint_gtm_planner.py, and revshare_modeler.py) used for deterministic logic and mathematical modeling. These scripts are implemented using only the Python standard library and do not perform any dangerous shell commands or unauthorized system interactions.
[DATA_EXFILTRATION]: No data exfiltration vectors were identified. The skill does not access sensitive file paths (e.g., credentials or environment files) and contains no network communication functionality such as curl or requests.
[PROMPT_INJECTION]: The skill instructions provide structured business guidance and do not attempt to bypass agent safety filters, override core instructions, or extract system prompts.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a data ingestion surface through its partnership intake template, which is processed by internal scripts. However, because the skill lacks exploitable capabilities—such as network access, arbitrary code execution, or filesystem writes—the risk of indirect injection is negligible.
[EXTERNAL_DOWNLOADS]: The skill is entirely self-contained and does not download or install external packages, scripts, or remote dependencies.

partnerships-architect