The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external index files and source documents which could potentially contain adversarial instructions designed to influence the agent's output.
Ingestion points: Reads context/learnings/index.md, context/index.json, and individual source documents referenced within the index.
Boundary markers: None specified; the skill does not use delimiters or instructions to ignore embedded commands within the retrieved text.
Capability inventory: Limited to file read operations within the local context directory. No network operations, shell command execution, or dynamic code evaluation capabilities are present.
Sanitization: No evidence of text sanitization or filtering of the retrieved content before it is presented to the user or used for recommendation generation.

relevant-learnings