The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses various shell commands including yarn build, yarn test:run, ls, and git status to manage the development workflow. These operations are restricted to the local repository and are consistent with the primary purpose of automating SDK testing for Sentry.
[PROMPT_INJECTION]: The skill incorporates user-provided inputs, such as test application names and variant flags, directly into shell command templates. This represents a surface for indirect prompt injection (Category 8).
Ingestion points: User input for <test-app-name> and <variant-name> defined in SKILL.md.
Boundary markers: No explicit boundary markers or sanitization logic is present to delimit user input from the shell command structure.
Capability inventory: The skill has the capability to execute shell commands via yarn and navigate the filesystem using ls and cd, as seen in SKILL.md steps 2, 3, and 4.
Sanitization: There is no evidence of input validation or sanitization to prevent command injection via malicious test application names.

e2e