The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data from repositories, which creates a potential attack surface.
Ingestion points: The skill uses Read, Glob, and Grep to inspect repository code, configuration, fixtures, and evidence (as specified in the 'Tool Discipline' section).
Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat this ingested repository content as untrusted or to ignore instructions embedded within those files.
Capability inventory: The skill allows the use of Write and Edit tools, enabling the agent to modify the filesystem based on its analysis.
Sanitization: The instructions do not define any sanitization or validation steps for content read from the repository before it is processed or used to inform file-writing actions.
[EXTERNAL_DOWNLOADS]: The skill references several external URLs for official AssemblyAI documentation and machine-readable guides on www.assemblyai.com. These are identified as legitimate first-party resources for the vendor's own services.

assemblyai-reference-architecture