The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest document content from external search indices (Elasticsearch or Algolia), transform it, and index it into a new platform. This creates a surface for indirect prompt injection where malicious instructions hidden in the source data could influence the agent's behavior during the migration or validation steps.
Ingestion points: The exportAndTransform function in SKILL.md scrolls through and reads document bodies and metadata from source search providers.
Boundary markers: No explicit delimiters or boundary markers are employed to isolate the ingested document content from the agent's operating instructions.
Capability inventory: The skill has access to Read, Write, Edit, and Bash tools, which could be misused if an injection occurs.
Sanitization: There is no evidence of content sanitization, escaping, or validation of the document bodies before they are processed by the agent.
[COMMAND_EXECUTION]: The skill includes a rollback plan that executes curl commands to interact with the Glean API for datasource management.
[EXTERNAL_DOWNLOADS]: The skill references and performs network requests to the official Glean developer documentation and API infrastructure (glean.com) during the migration and validation phases.

glean-migration-deep-dive