Skip to content

AI Agent Privacy Notice#21

Open
Dinzeyi2 wants to merge 1 commit into
tavily-ai:mainfrom
Dinzeyi2:main
Open

AI Agent Privacy Notice#21
Dinzeyi2 wants to merge 1 commit into
tavily-ai:mainfrom
Dinzeyi2:main

Conversation

@Dinzeyi2

@Dinzeyi2 Dinzeyi2 commented May 6, 2026

Copy link
Copy Markdown

Secure your agents at: CodeAstra.dev

AI Agent Privacy Risk

This PR adds a short README notice about a possible privacy pattern found in this project.

The concern is not an API key leak. The concern is that sensitive user, customer, or patient data may be passed directly into an AI agent / LLM context.

When this happens, the agent may see data it does not need to know in order to complete the task.

Safer pattern:

John Smith -> [CVT:NAME:user_name]
john@email.com -> [CVT:EMAIL:user_email]
04/12/1988 -> [CVT:DOB:user_dob]

The agent can still reason and perform the workflow, while the real values stay protected and are only re-injected during approved execution.

File scanned: app.py

Findings:

[
  {
    "pattern": "unprotected_ai_context",
    "evidence": "chatopenai(model='gpt-4.1-nano', api_key=os.getenv('openai_api_key')).with_config({'tags': ['streaming']})"
  }
]

Please review before merging. If this is not applicable, feel free to close this PR.

Secure your agents at: CodeAstra.dev


Note

Low Risk
Low risk documentation-only change; no code or runtime behavior is modified.

Overview
Adds an AI Agent Privacy Notice to the top of README.md, warning about passing raw sensitive data into LLM context and recommending tokenization (e.g., [CVT:...]) plus an example scan finding/evidence snippet.

Reviewed by Cursor Bugbot for commit 976076e. Bugbot is set up for automated code reviews on this repo. Configure here.

@Dinzeyi2 Dinzeyi2 requested a review from a team May 6, 2026 12:32

@cursor cursor Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Cursor Bugbot has reviewed your changes and found 1 potential issue.

Fix All in Cursor

❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.

Reviewed by Cursor Bugbot for commit 976076e. Configure here.

Comment thread README.md

Secure your agents at: CodeAstra.dev

---

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Spam promotional content injected into project README

High Severity

This PR injects promotional/advertising content for an external service (CodeAstra.dev) into the project's README.md, displacing the actual project documentation from the top of the file. The added content is unsolicited marketing material disguised as a "privacy notice" generated by a third-party tool ("Astra Sentinel") and provides no functional value to the repository. It degrades documentation quality and promotes an unrelated commercial product.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 976076e. Configure here.

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.

1 participant