Set up and diagnose local agentmemory, including MCP, environment variables, ports, and feature flags. Use when getting started, checking a connection, enabling a feature, configuring auth, or explaining why a feature is off by default.
86%
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
The 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 diagnostic path reads the local agentmemory status resource and calls `memory_sessions`, which can return previously captured session records that may include text from outsider-controlled web pages or tool output the agent handled earlier, though nothing outsiders post reaches this path directly.
rohitg00/agentmemory
cf9a738
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.