The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute several shell commands and local Python scripts located within the project repository, such as ai_dev_ssd_flow/06_SYS/scripts/validate_sys.py and ai_dev_ssd_flow/scripts/update_traceability_matrix.py. It also includes steps to run shell hooks located at ./hooks/pre_sys_generation.sh and ./hooks/post_sys_generation.sh.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its data processing workflow.
Ingestion points: It reads architecture decisions, system constraints, and requirements from upstream documents including ADR, BRD, and PRD markdown files in the docs/ directory.
Boundary markers: The instructions do not define explicit boundary markers or delimiters to separate the ingested data from the agent's internal logic or templates.
Capability inventory: The skill has the capability to execute local scripts and write generated markdown files to the docs/06_SYS/ directory.
Sanitization: There is no specified sanitization or validation of the content extracted from the input documents before it is used to populate the system requirements templates.

doc-sys-autopilot