The Agent Skills Directory

[PROMPT_INJECTION]: The skill implements an instruction override logic where content from external files (specifically .ai-factory/skill-context/aif-explore/SKILL.md) is prioritized over the skill's own defined rules.
[COMMAND_EXECUTION]: The skill is granted access to the Bash tool, enabling arbitrary command execution on the host environment for the purpose of codebase investigation.
[PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection because it ingests untrusted data from multiple project files and treats them as authoritative instructions.
Ingestion points: Multiple files including .ai-factory/DESCRIPTION.md, .ai-factory/ARCHITECTURE.md, .ai-factory/RULES.md, and .ai-factory/skill-context/aif-explore/SKILL.md.
Boundary markers: Not present; the skill lacks delimiters or warnings to ignore embedded instructions in these files.
Capability inventory: The skill can execute shell commands via Bash and modify files via Write and Edit.
Sanitization: No sanitization or validation of the content read from the project files is performed before it is integrated into the agent's context.

aif-explore