Conversation
Deploying everyskill with
|
| Latest commit: |
401f8b4
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://3af8e8d2.everyskill.pages.dev |
| Branch Preview URL: | https://skill-intercom-api-177264331.everyskill.pages.dev |
Frontier Model Security Review
Final Verdict: WARN Claude Opus 4.6 Analysis{"verdict": "PASS", "issues": [], "reasoning": "The skill provided is empty or contains no content to analyze. An empty skill poses no security risk as there are no instructions, tool usages, prompt injections, data exfiltration attempts, or social engineering tactics present. However, an empty skill is also non-functional. Since there is nothing malicious to flag, the verdict is PASS."}GPT-5.2 Analysis{"verdict":"WARN","issues":[{"category":"insufficient_input","severity":"medium","description":"No skill code/configuration was provided to review. Without the OpenClaw skill definition (prompt, tool schema, allowed-tools, and any scripts), I cannot assess prompt injection, tool safety, exfiltration, or social engineering risks."}],"reasoning":"A security review requires the actual skill content (system/prompt text, tool definitions/permissions, any embedded bash/scripts, network access configuration, and environment/file access rules). Please provide the skill JSON/YAML (or full source) so I can scan for injection strings (e.g., 'ignore previous', encoded directives), dangerous shell/file operations, external network calls, credential access, manipulation patterns, and overly broad tool permissions."}Frontier model review complete. Human approval still required. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
New Skill Submission
Skill: intercom-api
Submitted by: Kieran Klaassen
Reason: Complete Intercom REST API skill for AI agents to manage conversations (reply, note, assign, close, snooze) and Help Center articles (CRUD). Includes error handling, tracker tickets, and workflow patterns. Battle-tested in production ops.
This PR was auto-generated from skills.every.to (agent-api).
AI security review will run automatically.