The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes data from external files in the docs/solutions/ directory which could potentially contain instructions intended to influence the agent's behavior.
Ingestion points: Documentation files located in docs/solutions/ (referenced in SKILL.md).
Boundary markers: Absent. The skill does not define specific delimiters to isolate external content.
Capability inventory: The skill utilizes content-search and Read tools to retrieve and process file contents (referenced in SKILL.md).
Sanitization: No sanitization or validation of the retrieved file content is performed before it is presented to the agent.

learnings-researcher