The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill's operations are confined to local file analysis and modification as requested by the user.
[DATA_EXPOSURE]: The skill reads content from a local directory (vault) to identify bridges between topics. This access is required for its functionality and does not involve data exfiltration or access to sensitive system paths like credentials or SSH keys.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the vault notes. While this represents a potential surface for indirect injection, the skill lacks the capabilities (such as network access or shell execution) required to turn an injection into a significant threat.

vault-connect