Staff a task only from Agentlas agents registered on this machine.
72%
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-local/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's behavior is entirely delegated to an unreviewed sibling file, and it tells the agent not to summarize that file, which leaves the user unable to see what will run; this is opaque and plausibly hides activity, though no clear malicious intent is shown.
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.
This skill's only required runtime action is to read the sibling file `../hep-local/SKILL.md` and follow it, but that file is not in the input, so whether it ingests outsider-authored text cannot be verified.
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.