The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The README.md provides installation instructions using npx skills add emiliosheinz/agent-skills. This command fetches the skill package from the author's remote repository. This is a standard installation procedure for the platform.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied answers from the AskUserQuestion tool to guide its logic and build a "design tree". This represents a potential surface for indirect prompt injection where malicious instructions could be embedded in user responses.
Ingestion points: User answers received through the AskUserQuestion tool as described in SKILL.md.
Boundary markers: The instructions in SKILL.md do not specify the use of delimiters or "ignore embedded instructions" warnings for the data processed from the user.
Capability inventory: SKILL.md directs the agent to access the filesystem and dispatch sub-agents to "find facts" from the environment.
Sanitization: There are no instructions in SKILL.md for sanitizing or validating the input provided by the user before processing it into the decision tree logic.

grill