Trigger: a mapping need, parallel units, context backstop, high-risk verify, fresh review, or multi-step debug. Delegate via delegate_task for a named reason.
75%
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
Fix and improve this skill with Tessl
tessl review fix ./internal/assets/skills/hermes-ephemeral-delegation/SKILL.mdThe 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 skill names no external service; its only plausibly outsider-touched input is the "PR readiness" fresh-review path (SKILL.md line 17), which could pull in externally authored PR text if the agent fetches it, so I'm assigning low under the recall-first override.
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.