The Agent Skills Directory

[SAFE]: The skill implements production-grade customer success analytics using local Python scripts and markdown templates. The logic is transparent and follows standard software engineering practices.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns were detected. The scripts (health_score_calculator.py, churn_risk_analyzer.py, expansion_opportunity_scorer.py) use only Python's standard library and contain no eval(), exec(), or subprocess calls that could be used to execute arbitrary commands.
[DATA_EXFILTRATION]: No network activity or data exfiltration patterns were detected. The tools process data locally from provided JSON files and output results to stdout. No sensitive file paths (e.g., SSH keys, AWS credentials) are accessed by the scripts.
[OBFUSCATION]: The code and documentation are written in clear text with no signs of encoding, hidden characters, or homoglyph attacks. All logic is plainly visible and easily auditable.
[INDIRECT_PROMPT_INJECTION]: The tools ingest external JSON data for analysis but lack dangerous capabilities such as shell execution or network requests. The risk of exploitation via malicious input data is negligible as the tools only perform mathematical operations and text formatting.

customer-success-manager