The Agent Skills Directory

[SAFE]: The skill instructions direct the agent to scan the workspace for analytics-related artifacts such as configuration files for Metabase, Grafana, dbt, and Looker, as well as data warehouse connection configurations (BigQuery, Snowflake). While these files can contain sensitive information, the activity is consistent with the skill's primary stated purpose of conducting a business intelligence (BI) assessment and mapping data coverage.
[SAFE]: No suspicious network operations or data exfiltration patterns were detected. The skill primarily uses local tools like 'Grep', 'Glob', and 'Read' to perform its assessment.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were found in the skill's instructions or metadata.

lens-recon