specialist-support-support-executive-summary-generator

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text and framework definitions for a sub-agent. It does not request system-level permissions, hardcode credentials, or attempt to access restricted file paths.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external business data to generate summaries, which creates an inherent surface for indirect prompt injection. However, since the sub-agent has no access to sensitive capabilities such as file system writes, network operations, or shell execution, this surface does not represent a significant security risk.
  • Ingestion points: User-supplied business inputs processed by the spawned agent (SKILL.md).
  • Boundary markers: Absent; the prompt does not explicitly delimit user data from instructions.
  • Capability inventory: Limited to ephemeral sub-agent spawning for text generation (SKILL.md).
  • Sanitization: Absent; content is processed directly for summarization.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-support-support-executive-summary-generator