The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses ls -R tests/ to discover the project's test directory structure. This is a routine discovery operation for development tools.
[DATA_EXPOSURE]: Accesses project configuration files like package.json and playwright.config.ts to extract environment details (versions, timeouts, base URLs) necessary for generating accurate test plans.
[PROMPT_INJECTION]: The skill has an attack surface for Indirect Prompt Injection (Category 8) because it processes data from insights.md which could contain malicious instructions designed to influence the generated code blocks.
Ingestion points: .pst/sessions/[name]/insights.md and .pst/sessions/[name]/snapshots/.
Boundary markers: Absent. The skill reads and processes these files directly without using delimiters or instructions to ignore embedded commands.
Capability inventory: The skill is explicitly designed to generate full, runnable TypeScript code for Playwright tests and configuration files.
Sanitization: Absent. The skill does not perform validation or filtering on the ingested data before using it to generate the implementation plan.

pst-plan