The Agent Skills Directory

[SAFE]: Analysis of the skill instructions and metadata reveals no malicious patterns or security risks. The skill operates within the expected scope of its stated maintenance purpose.
[DATA_EXFILTRATION]: The skill accesses project-specific memory files (MEMORY.md) and personal memory files (personal-memory.md). While these files may contain sensitive project logic, the access is local and required for the consolidation task. No network tools are requested or used to send this data externally.
[PROMPT_INJECTION]: The skill ingests data from external sources (memory files) which represents an indirect prompt injection surface. This is mitigated by the skill's requirement for user confirmation via the AskUserQuestion tool before performing any write or edit actions, preventing automated execution of malicious instructions found in the data.

consolidate-memory