Search Agentlas Cloud and Hub agent candidates without invoking.
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./kimi/skills/agentlas-search/SKILL.mdDetected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is a thin pointer that delegates all behavior to a sibling file it does not show, and it forbids the agent from summarizing that file, so the user cannot see what the command will do; there is no direct evidence of malicious intent.
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 workflow delegates to an unseen sibling `hep-search/SKILL.md` and then searches Agentlas Hub agent candidates, a community marketplace whose listings are outsider-authored but only read after the agent actively searches for them.
agentlas-ai/Agentlas-OS
fdcd97a
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.