The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes artifact content or user-provided text through the $ARGUMENTS variable to identify claims and evidence, creating a surface for indirect prompt injection.
Ingestion Point: SKILL.md targets $ARGUMENTS or the current agent response as the analysis target.
Boundary Markers: The instructions lack explicit delimiters (like XML tags or triple quotes) or "ignore embedded instructions" warnings for the processed content.
Capability Inventory: The skill does not utilize any tools, file system access, or network operations. Its activity is restricted to logical analysis and Markdown response generation.
Sanitization: No specific sanitization, validation, or filtering of the input artifact content is defined.
[EXTERNAL_DOWNLOADS]: The README file provides links to the author's GitHub repository for installation (github.com/synapseradio/ai-skills) and license verification. These are standard references to the vendor's own infrastructure.

integrity