signals-scout-web-analytics
Signals scout for PostHog web traffic. Watches per-channel session volume, attribution breakage, and landing-page health (bounce / 404 steps) against the site's own baseline, and files each validated divergence as a report in the inbox. Per-page web vitals have their own dedicated `signals-scout-web-vitals`.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The skill “signals-scout-web-analytics” reads outsider-authored free-text indirectly at runtime via browser-captured session/event fields (e.g., `$entry_pathname`, `$entry_referring_domain`, `$entry_utm_*`, and 404-event candidate event/property values) that are ingested from untrusted traffic and then used in LLM-facing computations and report writing.
- Repository
- PostHog/posthog
- Commit
2a19010
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.