Operate notifications as one ECC-native workflow across GitHub, Linear, desktop alerts, hooks, and connected communication surfaces. Use when the real problem is alert routing, deduplication, escalation, or inbox collapse.
59
74%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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 SKILL.md workflow explicitly requires the agent to "capture" and "classify" events from third-party user-generated sources such as "GitHub issues, PRs, reviews, comments" and "Linear issue/project movement" (see "Preferred Surface" and "Event Pipeline"/"Workflow" sections), which the agent would read and use to decide routing/actions, creating a clear avenue for untrusted content to influence behavior.
GitHub issues, PRs, reviews, comments, and CI
content-type · 3 sites
The plugin instructs the agent to capture and classify events from GitHub issues, PRs, reviews, and comments — all user-generated third-party content that could contain prompt injection payloads influencing routing/action decisions.
SKILL.md
28
- GitHub issues, PRs, reviews, comments, and CI
SKILL.md
52
1. **Capture** the event
SKILL.md
53
2. **Classify** urgency and owner
Linear issue/project movement
content-type · 3 sites
The plugin instructs the agent to capture and classify events from Linear issue/project movement — third-party content that could contain prompt injection payloads influencing the agent's routing and action decisions.
SKILL.md
29
- Linear issue/project movement
SKILL.md
52
1. **Capture** the event
SKILL.md
53
2. **Classify** urgency and owner
connected email/chat surfaces
content-type · 3 sites
The plugin instructs the agent to capture and classify events from connected email/chat surfaces — email from external senders and chat messages from other users are third-party user-generated content that could contain prompt injection payloads influencing routing and action decisions.
SKILL.md
32
connected email/chat surfaces when they actually exist
SKILL.md
52
1. **Capture** the event
SKILL.md
53
2. **Classify** urgency and owner