The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the web via WebSearch and local project documentation in the docs/technology/ directory. This ingestion surface is a standard characteristic of AI agent skills but represents a potential vector for indirect prompt injection if external content contains adversarial instructions.
Ingestion points: Reads files from docs/technology/ and processes search results from the WebSearch tool.
Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands in the data it processes.
Capability inventory: The skill has capabilities to Read the codebase, Write to documentation, and Edit the HUMAN_AGENDA.md file.
Sanitization: No explicit sanitization or validation of the ingested content is described in the skill instructions.