Use when generating a single installable agent that should keep learning, track sources, refresh research, propose repairs, or improve itself over time without becoming a multi-agent team.
68%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./claude/plugins/agentlas-core-engine-meta-agent/runtime-support/skills/self-evolving-single-agent/SKILL.mdThe canonical home for this skill is self-evolving-single-agent in agentlas-ai/Agentlas-OS
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill directs the agent to install a public global command into several tools' global adapters and to add an optional scheduled workflow, which changes machine-level state beyond the project, though it never mentions sudo, accounts, SSH, or system service files.
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 builder workflow actively searches and fetches outsider-authored web content (similar agent repositories, comparables, and plugin docs) at lines 11-16, which the agent must select and pull in, so the risk is low rather than medium.
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.