The Agent Skills Directory

[PROMPT_INJECTION]: The skill ingests untrusted user input describing business processes, representing an indirect prompt injection surface.
Ingestion points: SKILL.md (Step 1 collects the FLOW variable from user input).
Boundary markers: Absent; there are no specific instructions to the agent to ignore potential instructions embedded within the process steps.
Capability inventory: The skill logic is limited to text analysis and report generation; no tools for network exfiltration or shell execution are invoked by the analysis process.
Sanitization: Absent; the skill does not specify any validation or filtering of the user-provided data.
[EXTERNAL_DOWNLOADS]: The skill includes a setup command that targets a repository on GitHub.
Evidence: npx skills add https://github.com/peter-tu-zynkr/zynkr-skill-builder in SKILL.md.
Context: This is a configuration and installation command for the skill's own ecosystem components.

operations-flow-optimization