The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts tech_debt_analyzer.py and team_scaling_calculator.py using the python command. These scripts are located in the vendor/c-level-advisor/cto-advisor/scripts/ directory relative to the plugin root, which is standard for secondary analysis tasks.
[INDIRECT_PROMPT_INJECTION]: The skill takes an architectural plan as user input, creating an ingestion point for potentially malicious instructions embedded in the processed data.
Ingestion points: The <plan> argument supplied to the /c-level-agents:cto-review command in SKILL.md.
Boundary markers: No delimiters, markers, or explicit instructions to ignore instructions within the input are provided in the skill definition.
Capability inventory: The skill is capable of executing code via Python scripts and generating structured architectural verdicts.
Sanitization: No sanitization or validation logic is defined for the plan input before it is utilized by the agent.

cto-review