Forget Something
v0.1.0Implement forgetting mechanisms for AI systems to manage memory overload, improve performance, and maintain data privacy. Use when working with long-term AI...
⭐ 0· 99·0 current·0 all-time
by@roryyu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description (forgetting mechanisms for AI agents) match the SKILL.md content. All examples and integration points reference agent memory, scheduler, logger, and configuration, which are appropriate for this purpose. No unrelated credentials, binaries, or install steps are requested.
Instruction Scope
The instructions stay focused on memory deletion strategies and OpenClaw integration. They do mention exposing functionality via API and cross-agent forgetting — these are reasonable extension points but imply additional security controls (authentication, authorization, audit logging) that the SKILL.md does not specify. The example code also contains minor implementation bugs (e.g., using Array.filter without reassigning or persisting deletions) but these are correctness issues rather than malicious scope creep.
Install Mechanism
Instruction-only skill with no install spec and no external downloads. Nothing will be written to disk by an installer as part of the skill itself.
Credentials
The skill requests no environment variables, credentials, or config paths. Its described integration uses the agent's existing memory, scheduler, and config, which is proportionate to the stated functionality.
Persistence & Privilege
The skill does schedule recurring forgetting tasks via the agent scheduler (normal for this function). It is not marked always:true. However, scheduled automatic deletion and any API endpoints/cross-agent forgetting capability increase operational risk if not protected — the SKILL.md does not detail access controls or backup storage specifics.
Assessment
This skill is a coherent, instruction-only guide for implementing forgetting strategies. Before installing or enabling it: (1) confirm where backups are stored and that backups are encrypted and access-controlled, (2) require and verify authentication/authorization for any API endpoints that trigger forgetting, (3) test using dryRun and conservative settings to ensure deletions behave as you expect (the examples may not persist deletions as written), (4) add audit logging and retention to track what was removed, and (5) if you enable cross-agent or scheduled forgetting, restrict who can change the schedule or config. If you need, ask the author for concrete storage/backup and API security details before enabling automatic runs.Like a lobster shell, security has layers — review code before you run it.
latestvk9751zzrwg4wjf7ftb617hgw1x832cy7
License
MIT-0
Free to use, modify, and redistribute. No attribution required.