The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes and encourages the execution of local Python scripts (tech_debt_analyzer.py and team_scaling_calculator.py) to perform management calculations. Analysis of these scripts confirms they are benign, containing only mathematical logic and report-generation code without any network requests, file system writes, or dynamic code execution.
[PROMPT_INJECTION]: The skill exhibits two low-severity findings: a metadata inconsistency where the author listed in the YAML frontmatter ('Alireza Rezvani') differs from the context ('jasonnoahchoi'), and an inherent surface for indirect prompt injection due to its data-processing functions.
Ingestion points: The scripts in the scripts/ directory ingest system and team configuration data as dictionaries to calculate metrics.
Boundary markers: No explicit boundary markers or isolation instructions are present in the scripts to protect against instructions embedded in the ingested data.
Capability inventory: No subprocess calls, exec/eval, file-write, or network operations are present in tech_debt_analyzer.py or team_scaling_calculator.py.
Sanitization: The scripts process data using standard dictionary lookups and numerical operations but do not perform sanitization on string inputs.
[SAFE]: No critical or high-risk malicious patterns such as credential theft, obfuscation, or remote code execution from untrusted sources were detected. The skill's behavior is consistent with its stated purpose of providing technical strategy guidance.

cto-advisor