feat: add pii-bouncer skill#170
Draft
joethreepwood wants to merge 1 commit into
Draft
Conversation
The instructions for the wizard's PII Bouncer program (PostHog/wizard#510). A docs-only remediation skill that hardens a frontend against PII leaking into session replay and autocapture: - adds the `ph-no-capture` class to sensitive elements - tightens session_recording mask config (maskTextSelector; confirms maskAllInputs is not disabled — it defaults to true) - writes posthog-pii-bouncer-report.md shared_docs inlines the authoritative privacy + js/config docs as references/ so the agent uses real option names, not guesses. Emits the [ABORT] signals the wizard program routes (no-posthog-js / no-init-call / no-frontend-templates). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
🧙 Wizard CIRun the Wizard CI and test your changes against wizard-workbench example apps by replying with a GitHub comment using one of the following commands: Test all apps:
Test all apps in a directory:
Test an individual app:
Show more apps
Results will be posted here when complete. |
6 tasks
Member
|
@joethreepwood this is a perfectly constructed context mill skill 👏 i don't even have to read it. you can tell just by the shape and how you're stitching posthog docs as a reference with your skill instructions |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The context-mill skill ("cartridge") for the wizard's PII Bouncer program — companion to PostHog/wizard#510. The wizard side is pure engine; this is the packaged-English methodology it loads at runtime.
pii-bounceris a docs-only remediation skill that hardens a frontend against PII leaking into session replay and autocapture:ph-no-captureclass to sensitive elements (the replay-masking mechanism — distinct from thedata-ph-no-captureautocapture attribute)session_recordingmask config: addsmaskTextSelectorfor sensitive text (not masked by default) and confirmsmaskAllInputsisn't disabled (it defaults totrue, so inputs are already masked — the skill doesn't restate that)posthog-pii-bouncer-report.md(elements masked + why, init changes, reviewed-but-skipped, manual follow-ups)Design
type: docs-only, single variantid: all→ skill idpii-bouncer(matches the wizard'sskillId).shared_docspulls insession-replay/privacy.md+libraries/js/config.md, bundled asreferences/so the agent uses the authoritative option names and defaults instead of guessing.[ABORT]signals the wizard routes verbatim:no-posthog-js,no-init-call,no-frontend-templates.This is complementary to the new warlock PII rules: warlock stops PII being sent as event properties; this skill stops PII being recorded in the DOM.
Test plan
pnpm buildproducesdist/skills/pii-bouncer.zipcontainingSKILL.md+references/{privacy,config}.mdpii-bouncerappears inskill-menu.jsonpnpm devserves it athttp://localhost:8765; the wizard (localMcp) resolves + downloads itpii-bounceragainst a workbench app and confirm the masking edits + report🤖 Generated with Claude Code