The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a Python-based driver script located at ${CLAUDE_PLUGIN_ROOT}/tools/saga_driver.py to orchestrate the generation and audit workflow.
[PRIVILEGE_ESCALATION]: The execution command includes the --allow-skip-permissions flag, which explicitly instructs the agent to bypass standard platform permission prompts for file writes to enable unattended execution.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted data to drive file generation and logic.
Ingestion points: The skill accepts free-text prompts, BRD (Business Requirements Document) files, and IPLAN (Implementation Plan) files as primary inputs for generation (SKILL.md).
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the input data are defined in the orchestration logic.
Capability inventory: The skill has the capability to execute shell commands via saga_driver.py and perform file system write operations to the docs/02_PRD/ directory (SKILL.md).
Sanitization: There is no evidence of sanitization or validation of the input content before it is processed by the generation driver.

doc-prd-autopilot