messages-ops

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external messaging platforms such as iMessage, social DMs, and browser-gated surfaces, which creates a surface for indirect prompt injection.
  • Ingestion points: Live message threads, social media DMs, and local messaging surfaces (SKILL.md).
  • Boundary markers: The instructions do not provide explicit delimiters or directives to ignore instructions embedded within the retrieved messages.
  • Capability inventory: The agent is instructed to read threads and can hand off data to other capabilities such as knowledge-ops or lead-intelligence (SKILL.md).
  • Sanitization: No sanitization or validation of the incoming message data is defined in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 11:45 PM