The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional text and prompt structures for performing intellectual property research tasks. It does not include any scripts, executable binaries, or system commands.
[SAFE]: No network operations, data exfiltration patterns, or external downloads were detected. The skill operates purely within the conversational context provided by the agent.
[SAFE]: The instructions include strong safety and governance warnings, explicitly directing users to seek professional legal counsel and identifying red flags in legal documents, which aligns with safety best practices.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data such as technology descriptions, competitor names, and contract text.
Ingestion points: Input variables like technology descriptions and contract clauses in SKILL.md.
Boundary markers: The skill does not define specific delimiters for separating user data from instructions.
Capability inventory: The skill does not utilize any file-writing, network, or code execution capabilities.
Sanitization: No explicit sanitization or filtering of input data is defined within the skill instructions.

ip-protection