taskflow-inbox-triage

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a pattern for processing inbox messages, which is an indirect prompt injection surface because it ingests untrusted external data that could contain malicious instructions.
  • Ingestion points: The skill ingests 'inbox items' and 'messages' for classification (referenced in SKILL.md).
  • Boundary markers: No boundary markers or instructions to ignore embedded commands are present in the provided pattern.
  • Capability inventory: The skill has the capability to post to Slack and generate summaries based on the processed data.
  • Sanitization: The implementation logic does not show any sanitization or validation of the input content before it is passed to the classification or routing steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 04:50 AM