session-replay
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external session replay recordings and wireframes from web or mobile applications. This data is converted into text-based timelines and DataFrames for agent analysis.
- Ingestion points: Untrusted data enters the context via
ws.replays_for_user()andws.fetch_replays()inSKILL.md. - Boundary markers: The recording data is parsed into structured
pandas.DataFrameobjects and Markdown action timelines. - Capability inventory: The skill has access to
Bash,Read,Write, andEdittools as configured in the frontmatter. - Sanitization: The documentation notes that masked text is excluded by the SDK and provides instructions to keep bearer credentials in signed URLs masked during output.
- [EXTERNAL_DOWNLOADS]: The skill fetches tutorials and API documentation from Mixpanel's official GitHub-hosted documentation site.
Audit Metadata