PostHog / PostHog/ai-plugin

POSTHOG_LLMA_PRIVACY_MODE=true doesn't apply to error

Open
#120 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
84
Forks
15
Avg merge
14h 34m
Merged PRs (30d)
7

Description

On any tool error, up to 500 chars of that tool's output/stderr/content is transmitted to PostHog even with privacy mode on — that can include file contents, command output, secrets in error text, etc.

It's built from the failing tool's error/content and doesn't appear to have the privacy mode guards:
str(result.get("error", result.get("content","")))[:500]

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Search the repository for the shown result.get("error", result.get("content", "")) expression and inspect the surrounding privacy-mode guards. Trace how tool errors are assembled and transmitted, then locate the relevant tests or test entry point. Done means privacy mode no longer sends tool error output while normal-mode behavior remains covered by regression tests.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
security
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
55/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.