The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external project documentation to inform technical decision-making and document generation.
Ingestion points: Core requirements and interactions are extracted from local files docs/02-方案设计/PRD产品需求文档.md and docs/02-方案设计/原型设计方案.md in Step 2 and Step 3.
Boundary markers: The instructions do not define explicit boundary delimiters or "ignore embedded instructions" directives when interpolating content from these external files into the agent's context.
Capability inventory: The skill has Read and Write access to the filesystem, executes Bash for environment checks, and uses the Agent tool to dispatch tasks to subagents.
Sanitization: There is no logic provided to sanitize or validate the content retrieved from the ingested documents before it is processed or used to generate the final technical report.
[COMMAND_EXECUTION]: The skill executes a Bash script in the Preamble to verify the environment.
Evidence: The script uses echo and [ -f ... ] to check for the presence of required documentation. These operations are limited to environment verification and are safe within the intended use case.

pm-tech