The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute a Python validation script via the command python3 workflows/validate_tasks.py .maestro/<slug>/backend/tasks.json. The direct interpolation of the <slug> variable into the shell command string creates a potential command injection risk if the variable is derived from untrusted input and not properly sanitized.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external design and contract documents to generate its output. Ingestion points: Data is read from feature, contract_summary, lld_path, and project files such as .maestro/<slug>/lld/backend.md. Boundary markers: No specific delimiters or instructions to ignore instructions embedded within the ingested data are defined. Capability inventory: The skill utilizes the Bash tool for script execution and the Write tool for file creation. Sanitization: There is no evidence of input validation or content filtering before the processed data is used in the workflow.

backend-tasks