The Agent Skills Directory

[UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill invokes npx ai-devkit@latest, which dynamically downloads and executes the latest version of the ai-devkit package from the npm registry during the execution of testing tasks.
[COMMAND_EXECUTION]: The agent is instructed to execute shell commands using npx to perform automated linting and validation of feature testing coverage.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external documentation which could potentially contain malicious instructions. 1. Ingestion points: The agent reads external testing documents, requirements, design files, and implementation notes as described in SKILL.md. 2. Boundary markers: Absent; there are no delimiters defined to separate untrusted external content from the agent's instructions. 3. Capability inventory: The agent has the ability to execute shell commands and perform file-system write operations to update test suites and documentation. 4. Sanitization: Absent; the skill does not specify any content validation or sanitization for the documents it processes.

dev-testing