The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided project goals and definitions, which introduces an indirect prompt injection surface.
Ingestion points: The skill reads project metadata and requirements from learning/project.md and processes interactive chat input from the user.
Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions when reading the project file.
Capability inventory: The skill is limited to chat interaction and the creation of Markdown files (learning/plan.md, learning/knowledge-graph.md, learning/file-map.md) within the project directory.
Sanitization: Absent; the skill does not explicitly perform sanitization or validation of the input data before incorporating it into the generated documentation.
[SAFE]: The skill's behavior is restricted to instructional dialogue and documentation generation. It does not access sensitive credentials, perform network operations, or execute arbitrary code.

plan-journey