The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from the local project environment which creates a surface for indirect prompt injection.
Ingestion points: Reads project files, documentation, and recent git commits during the 'Explore project context' phase in SKILL.md.
Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent to ignore instructions embedded within the files it reads.
Capability inventory: The skill has the capability to write design documents to the file system (docs/plans/), commit changes to git, and invoke subsequent skills like writing-plans as defined in the 'Process Flow' and 'Documentation' sections of SKILL.md.
Sanitization: There is no evidence of sanitization or validation of the content read from the project files before it is used to generate design documents or influence tool calls.

brainstorming