daily-outlook-triage

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill ingests untrusted data from email subjects, senders, and calendar events (SKILL.md). There are no boundary markers or delimiters defined to isolate this external content from the agent instructions, and no sanitization or filtering is performed. While this creates a potential surface for indirect prompt injection, the risk is significantly lowered because the skill's capability inventory is limited to read-only operations via the workiq tool and lacks any tools for network exfiltration or file system modifications.
  • Data Access and Processing: The skill accesses sensitive user profile and communication data to generate triage summaries, which is its core functionality and is managed through the vendor's toolset.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 01:28 PM