skills/rerun-io/rerun/rerun-mcap/Gen Agent Trust Hub

rerun-mcap

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external MCAP files, which constitutes an attack surface where untrusted data could influence the agent's context.
  • Ingestion points: Processes files via mcap_path as described in SKILL.md.
  • Boundary markers: No specific delimiters or warnings for embedded instructions are provided in the ingestion logic.
  • Capability inventory: Uses McapReader and custom decoders to process data streams into chunks.
  • Sanitization: The instructions do not specify sanitization for message payloads or schema metadata.
  • [EXTERNAL_DOWNLOADS]: The skill references example code and pipelines located in the official Rerun GitHub repository.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the mcap Python library for low-level data access.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 03:32 PM
Security Audit — agent-trust-hub — rerun-mcap