The Agent Skills Directory

[NO_CODE]: The skill consists entirely of instructional documentation and templates in Markdown format. There are no executable scripts (Python, JavaScript, Shell), binaries, or configuration files.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze user-provided data such as product proposals and strategy documents. (1) Ingestion points: Untrusted data enters the agent context from user-supplied proposals in the conversation. (2) Boundary markers: The instructions do not specify any delimiters (e.g., XML tags or markdown blocks) to isolate untrusted data from the framework's instructions. (3) Capability inventory: The skill defines no tools, file system access, network operations, or subprocess execution capabilities across any of its files. (4) Sanitization: No sanitization or escaping of user-provided content is performed. While the ingestion surface exists, the complete absence of actionable capabilities (read/write/execute/network) renders the risk negligible.

the-challenger