The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied technical data which represents an indirect injection surface. Ingestion points: Technical system descriptions or code provided by the user for analysis in SKILL.md. Boundary markers: The skill does not specify the use of delimiters or 'ignore' instructions for analyzed content. Capability inventory: No file-write, network, or code execution capabilities are defined in the skill body or dependencies. Sanitization: No sanitization or filtering of external content is specified.
[NO_CODE]: The skill is documentation-only and does not include any executable code. Evidence: The skill comprises only the SKILL.md file with no scripts, package configurations, or binary assets.

arcana