The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends the use of a community-maintained CLI package (@11joselu/cypress-to-playwright) for automated migration tasks. This introduces a dependency on an unverified third-party package from a non-trusted author, which could pose a supply chain risk if the package is compromised.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process existing test suites for migration, creating a surface for indirect prompt injection where instructions hidden in the source code could influence the agent's behavior during the translation process.
Ingestion points: Phase 4 of the Migration Workflow in SKILL.md ("read the old one and understand what it actually verifies").
Boundary markers: The instructions do not define clear delimiters or warnings to ignore embedded instructions within the source test files.
Capability inventory: The skill suggests high-privilege capabilities including command execution via npx and the use of autonomous AI agents for code generation.
Sanitization: There are no instructions provided for sanitizing or validating external test content before the agent processes it.

test-migration