The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes local or external source files to extract titles and descriptions for a list of resources. This creates an attack surface where malicious instructions embedded in those source files could influence the agent's behavior during the analysis phase.
Ingestion points: The skill reads src/content/llms.txt and various source files associated with new links to be added.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt logic.
Capability inventory: The skill has the capability to read from the filesystem and write updates to documentation files.
Sanitization: There is no evidence of sanitization or validation of the content read from source files before it is processed by the model.

update-llms-text