The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process untrusted external data such as store reviews and support tickets to inform customer journeys.
Ingestion points: SKILL.md (instructions to read store reviews and support queue), research-evidence.md (synthesis of research findings into the foundation).
Boundary markers: Absent. No specific delimiters or "ignore embedded instructions" warnings are provided for the ingested external text.
Capability inventory: The skill executes local Python scripts (docs/ux/lint.py), performs file I/O operations, and invokes various Figma MCP tools.
Sanitization: Absent. The skill does not prescribe specific validation, escaping, or filtering of the external content before it is interpolated into the agent's context.
[EXTERNAL_DOWNLOADS]: The skill recommends the installation of external companion plugins and packages.
Evidence: visual-identity.md and system-map.md suggest the installation of sheleg-design-skill and task-pipeline using commands like /plugin install sheleg-design@sheleg-design-skill and npx sheleg-design-skill.
Note: These resources are identified as vendor-owned tools belonging to the author ssheleg and represent expected functionality for this ecosystem.
[COMMAND_EXECUTION]: The skill involves the execution of local utility scripts for maintenance.
Evidence: SKILL.md specifies the use of python3 docs/ux/lint.py to validate project documentation. This is a standard developer tool pattern for maintaining documentation consistency.

ux-foundation