The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from TestRail (titles, preconditions, steps) to generate Playwright tests and update TestRail records.
Ingestion points: Data enters the agent's context through the testrail_get_cases MCP tool (SKILL.md).
Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions that might be embedded within the external test case data.
Capability inventory: The skill has the ability to write test files, execute shell commands (npx playwright test), and perform network operations via TestRail MCP tools.
Sanitization: There is no mention of sanitizing, escaping, or validating the external content retrieved from TestRail before it is interpolated into code templates or processed by the agent.
[DYNAMIC_EXECUTION]: The skill generates executable scripts at runtime based on external input.
The 'Import Test Cases' capability fetches data from TestRail and dynamically generates Playwright .spec files.
The 'Push Test Results' capability subsequently executes these generated files using the npx playwright test command.
This pattern of script generation from untrusted external data followed by execution presents a risk if the source data is compromised.

testrail