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() and ws.fetch_replays() in SKILL.md.
  • Boundary markers: The recording data is parsed into structured pandas.DataFrame objects and Markdown action timelines.
  • Capability inventory: The skill has access to Bash, Read, Write, and Edit tools 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
Risk Level
SAFE
Analyzed
Oct 12, 2026, 03:23 PM