The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run common development commands like npm run build, node --test, and npm run dev. These are contextually appropriate for the stated purpose of verifying local software behavior.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes external data such as API responses, UI snapshots, and test artifacts to produce a verdict. This creates an interface for processing potentially untrusted data.
Ingestion points: Captured artifacts from APIs, UI snapshots, and local test outputs described in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded content within artifacts are provided.
Capability inventory: Capabilities include executing shell commands via node and npm scripts as defined in the 'Local surfaces' section of SKILL.md.
Sanitization: No explicit sanitization or validation of the content within the captured artifacts is described.

verify-this