The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to audit and review external web interfaces and UI code. This introduces a surface for indirect prompt injection, where an attacker could place malicious instructions within the content of a web page or code branch being audited.\n
Ingestion Point: The skill ingests data via node ../seenry/scripts/audit_page.mjs <url or file> and by rendering and screenshotting external URLs.\n
Capability Inventory: The agent has the capability to execute shell commands (node, git), access the file system (via git and local file rendering), and use MCP tools to fetch design data.\n
Boundary Markers: The instructions do not define clear delimiters or "ignore" instructions for the content being reviewed.\n
Sanitization: There is no explicit sanitization or filtering of the external content before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill uses standard CLI tools (git, node) to perform its primary function of auditing code and web pages. It executes several local scripts located in ../seenry/scripts/.\n- [DYNAMIC_EXECUTION]: The skill executes local Node.js scripts at runtime to perform UI audits.

seenry-review