The Agent Skills Directory

[SAFE]: The skill is composed entirely of natural language instructions designed to guide the AI's reasoning process. It does not contain any executable scripts, binaries, or configuration files that could perform actions on the host system.
[EXTERNAL_DOWNLOADS]: The README.md file contains installation instructions pointing to the author's GitHub repository (github.com/synapseradio/ai-skills) and links to academic papers for reference. These downloads are associated with the skill's distribution and documentation, and they target the author's own infrastructure or established academic domains.
[INDIRECT_PROMPT_INJECTION]: The skill defines a command (/situate) that accepts user-supplied subjects for analysis.
Ingestion points: The SKILL.md file interpolates the user-defined subject into analytical steps.
Boundary markers: None explicitly defined in the logic.
Capability inventory: None. The skill does not possess capabilities for network requests, file writing, or command execution.
Sanitization: None. However, because the skill has no side-effect capabilities, the risk of exploitation is negligible.

situate