The Agent Skills Directory

[SAFE]: The skill instructions are focused on knowledge management tasks within a specific local directory. No indicators of obfuscation, remote code execution, or data exfiltration were found.
[PROMPT_INJECTION]: The skill ingests user notes as untrusted data which is an inherent surface for indirect prompt injection. This is noted as a risk factor typical of the skill's purpose.
Ingestion points: File reading from the Brain/02-Permanent/ directory.
Boundary markers: No delimiters are used to wrap external content.
Capability inventory: The skill utilizes Read, Grep, Glob, and Write tools.
Sanitization: No content validation is performed on the analyzed text.

find-connections