Poll RSS, JSON APIs, and GitHub with watermark dedup.
77%
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 ./optional-skills/devops/watchers/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 workflow monitors RSS feeds, JSON APIs, and GitHub issues/pull requests where outsiders can author free text that gets ingested and delivered to the agent.
NousResearch/hermes-agent
d1b46d7
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.