Use when managing, triaging, restarting, escalating, or summarizing Codewhale fleet runs and workers.
88%
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 fleet manager skill reads Codewhale fleet run logs, artifacts, and worker inspect data, which may contain untrusted execution output or outsider-authored task payloads.
Hmbown/Codewhale
ff466b2
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.