Skip to content

Conversation

@phazonoverload
Copy link
Collaborator

This pull request adds a security notice to the README.md file to inform users about potential risks associated with workflows that accept user input.

Copilot AI review requested due to automatic review settings July 28, 2025 19:31
Copy link

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This pull request adds a security notice to the README.md file to warn users about potential prompt injection attacks when using workflows that accept user input. The notice provides guidance on mitigation strategies including careful prompt design and minimum permissions.

  • Adds an important security callout about prompt injection risks
  • Provides basic mitigation recommendations for workflows accepting user input

README.md Outdated
| [Add Merged PR to Changelog](/workflows/add-merged-pr-to-changelog/add-merged-pr-to-changelog.yml) | Appends a summary of a merged pull request to an issue. | @phazonoverload |

> [!IMPORTANT]
> Whenever workflows explicitly accept user input, a malicious actor could open an issue instructing a model to do something you don't want. By carefully writing prompts and providing minimum permissions, you can help mitigate these risks.

This comment was marked as off-topic.

README.md Outdated
| [Add Merged PR to Changelog](/workflows/add-merged-pr-to-changelog/add-merged-pr-to-changelog.yml) | Appends a summary of a merged pull request to an issue. | @phazonoverload |

> [!IMPORTANT]
> Whenever workflows explicitly accept user input, a malicious actor could open an issue instructing a model to do something you don't want. By carefully writing prompts and providing minimum permissions, you can help mitigate these risks.

This comment was marked as off-topic.

Copy link
Contributor

@Jeffrey-Luszcz Jeffrey-Luszcz left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@Jeffrey-Luszcz Jeffrey-Luszcz merged commit c416469 into main Jul 28, 2025
@Jeffrey-Luszcz Jeffrey-Luszcz deleted the prompt-injection-attack-callout branch July 28, 2025 19:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants