specialist-engineering-incident-response-commander

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface where untrusted user data is interpolated directly into the subagent instructions.
  • Ingestion points: The variable {the user's question} in SKILL.md is passed directly into the Agent tool's prompt argument.
  • Boundary markers: Absent. There are no delimiters (such as XML tags or unique markers) to clearly separate user-provided content from the system's instructions.
  • Capability inventory: The skill utilizes the Agent tool to spawn a subagent which may inherit broad capabilities from the host environment.
  • Sanitization: The instructions do not include any validation, escaping, or filtering for the interpolated user content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-engineering-incident-response-commander