The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill relies on the @scoutqa/cli package from the public NPM registry for its core functionality.
Evidence: The troubleshooting section in SKILL.md provides the installation command npm i -g @scoutqa/cli@latest.
[COMMAND_EXECUTION]: The skill uses the scoutqa command-line interface to interact with a remote testing service.
Evidence: The testing workflow utilizes commands like scoutqa --url "https://example.com" --prompt "..." and scoutqa send-message --execution-id ....
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted user data (URLs and test instructions) which are then interpreted by the remote ScoutQA agent.
Ingestion points: External data enters through the --url and --prompt parameters in SKILL.md.
Boundary markers: No specific delimiters or boundary warnings are used when interpolating user-provided instructions into the command string.
Capability inventory: The skill possesses the capability to execute shell commands via the Bash tool and send arbitrary natural language prompts to a remote autonomous testing agent.
Sanitization: There is no evidence of input validation or escaping for the user-supplied strings before they are passed to the CLI.

scoutqa-test