Turn meeting transcripts, conversation logs, or pasted documents into structured Basic Memory notes: match existing entities, propose new ones with approval, and capture action items.
74%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/memory-ingest/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow ingests user-pasted transcripts, emails, and articles (Step 1, lines 43-50), which can contain outsider-authored text, but the user chooses what to paste and nothing is monitored or auto-delivered, so an outsider cannot force delivery. Step 4's web research (lines 102-103) also reads outsider-authored web results the agent actively searches for, which is low risk.
basicmachines-co/basic-memory
4519c23
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.