The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references methodology and grounding materials from well-known organizations including the UK Government, MIT Sloan Management Review, OECD, and Shell. It also links to the author's official GitHub repository for skill-graph context.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather external market signals and research data, creating a potential surface for indirect prompt injection. * Ingestion points: Strategic drivers and evidence gathered via WebSearch and WebFetch in the 'Gather drivers and evidence' workflow (SKILL.md). * Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings for the data fetched from the web. * Capability inventory: The skill uses WebSearch and WebFetch to retrieve external content for constructing scenario narratives. * Sanitization: No specific validation or sanitization routines are defined for content retrieved from external websites before it is processed by the agent.

scenario-planning