The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from local markdown files, creating a vulnerability surface for indirect instructions to influence the agent's behavior.
Ingestion points: Reads content from profile.md, goals.md, projects.md, tools-learned.md, and .config.md within a user-configured folder (defaulting to ~/goal-driven-ai-context/).
Boundary markers: No specific delimiters or instructions to ignore embedded prompts are defined for processing these files.
Capability inventory: The skill has the ability to read and write files within the user's home directory and the specified context folder.
Sanitization: There is no evidence of sanitization, validation, or escaping of the content read from these external files before it is processed by the agent.

lab-context