The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to read and prioritize project-specific rules from files like .ai-factory/skill-context/aif-explore/SKILL.md. This creates a surface where instructions embedded in the project repository can override the skill's own safety constraints.\n
Ingestion points: Processes project files including .ai-factory/skill-context/aif-explore/SKILL.md, .ai-factory/DESCRIPTION.md, .ai-factory/ARCHITECTURE.md, RULES.md, and plan files.\n
Boundary markers: The skill uses specific marker tags like  for its own research data but lacks clear delimiters to prevent the agent from following instructions found in general project context files.\n
Capability inventory: The agent has access to Read, Glob, Grep, Write, Edit, Bash, and Task tools.\n
Sanitization: No sanitization or validation is performed on the content of the project context files before they are processed.\n- [COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool for local environment tasks, such as creating directories with mkdir -p and retrieving the current git branch using git branch --show-current to resolve plan paths.

aif-explore