The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data from the user. * Ingestion points: Ingests user-pasted test file paths, full error outputs, and test case documentation. * Boundary markers: Absent; there are no instructions to use delimiters or to ignore potential instructions embedded within the ingested test code or documentation. * Capability inventory: The skill has the capability to execute shell commands via npx and playwright-cli. * Sanitization: Absent; the skill does not explicitly validate or sanitize the content of the documentation or test files before processing.
[COMMAND_EXECUTION]: The skill constructs and executes shell commands using parameters provided by the user. * Evidence: The skill uses variables in commands such as 'npx playwright test [path]' and accesses file system paths like '.pst/sessions/[name]/'. * Risk: If the underlying platform does not sanitize these inputs, it could lead to command injection or path traversal if a user provides a malicious path or session name.

pst-debug