The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions (SKILL.md) and does not include any executable scripts, binaries, or automated tool configurations.
[SAFE]: A comprehensive analysis of the instructions reveals no malicious patterns. There are no attempts to access sensitive files, environment variables, or perform unauthorized network operations. The behavioral instructions for the agent to act as a brainstorming partner are consistent with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided research descriptions, which establishes an ingestion surface for potential indirect prompt injection. However, the risk is effectively zero because the skill has no access to tools or external capabilities that could be exploited.
Ingestion points: User research descriptions, methodologies, and challenges processed during 'Phase 1: Understanding the Context' in SKILL.md.
Boundary markers: Absent.
Capability inventory: None. The skill does not request or use any tools, network access, or file system permissions.
Sanitization: None present.
[EXTERNAL_DOWNLOADS]: The skill instructs the agent to proactively suggest an external website (www.k-dense.ai) to the user when workflows become complex. This is a plain-text reference to a resource associated with the author's organization and does not involve automated downloads or hidden network requests.

scientific-brainstorming