The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted data from multiple external sources to generate its test plans.
Ingestion points: The skill reads issue titles and descriptions via gh issue list, scans file contents using rg, and captures browser DOM structures through playwright-cli snapshot as described in references/discovery-sources.md and references/exploration-with-playwright.md.
Boundary markers: There are no instructions for the agent to use delimiters or specific safety warnings to ignore instructions embedded within the data being analyzed.
Capability inventory: The skill possesses the ability to execute shell commands (gh, rg, git, fd) and interact with a browser via playwright-cli.
Sanitization: The instructions do not specify any validation or sanitization steps for the data retrieved from the codebase or issue tracker.
[COMMAND_EXECUTION]: The skill utilizes several command-line interface (CLI) tools to perform project discovery and analysis.
Evidence includes instructions to use gh issue list for retrieving bug reports, rg and fd for searching the repository, and git log for analyzing change history.
It also integrates with a separate skill, playwright-cli, to perform browser-based exploration of the application's user interface.

e2e-flow-planner