The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill traces and reads codebase content to synthesize architectural explanations, which presents a surface for instructions embedded in the code to influence the agent's output.
Ingestion points: Codebase files accessed via Read, Grep, and Glob tools as defined in references/explainer-prompt.md.
Boundary markers: Absent; the prompts do not instruct the agent to ignore or delimit instructions found within the code being analyzed.
Capability inventory: Read-only access to the filesystem (Read, Grep, Glob) and synthesis of information for the user; the skill delegates more complex tasks like model reconciliation to the /domain-modeling tool.
Sanitization: Absent; the agent is instructed to use code snippets and prose directly from its findings without specific sanitization of the content.

pstack-how