The Agent Skills Directory

[SAFE]: No malicious code, obfuscation, persistence mechanisms, or unauthorized privilege escalation patterns were detected. The skill functions as a set of natural language instructions for text generation.- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection via the processing of external data. Ingestion points: Instructions direct the agent to read project context files such as .cursor/project-context.md or .claude/project-context.md and process user-supplied copy. Boundary markers: No specific delimiters or safety instructions are used to isolate ingested data from the skill's instructions. Capability inventory: The skill does not utilize any tools, execute shell commands, perform network requests, or write to the file system. Sanitization: No sanitization or validation of ingested content is performed. Given the absence of executable capabilities, this injection surface is assessed as safe.

blitz-copy