executive-assistant-expert

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions direct the agent to process untrusted data from email inboxes and the web, which is a known vector for indirect prompt injection attacks.
  • Ingestion points: Instructions for inbox triage, meeting design based on external requests, and web content analysis via WebFetch and mcp__scout__readable_text.
  • Boundary markers: Absent. The skill does not instruct the agent to use delimiters or ignore embedded instructions when processing external data.
  • Capability inventory: The skill has access to file reading (Read), web searching (WebSearch), and web fetching (WebFetch).
  • Sanitization: Absent. There are no instructions to sanitize, escape, or validate the content retrieved from external sources before it is incorporated into the agent's context.
  • [NO_CODE]: The skill consists entirely of natural language instructions in markdown and does not include any executable scripts, binaries, or configuration files that could pose a direct execution risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 03:51 AM
Security Audit — agent-trust-hub — executive-assistant-expert