specialist-engineering-senior-developer

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses a template that interpolates the user's question directly into the system prompt of a spawned sub-agent. This creates an indirect prompt injection surface where a malicious user query could attempt to override the sub-agent's instructions.
  • Ingestion points: The {the user's question} variable is placed at the end of the Agent tool's prompt string in SKILL.md.
  • Boundary markers: None. The user-provided content is not wrapped in delimiters (like XML tags or specific quotation markers) that would help the model distinguish between instructions and data.
  • Capability inventory: The spawned asa:engineering:Senior-Developer sub-agent is designed for full-stack engineering tasks, which typically implies capabilities for file system interaction and code generation.
  • Sanitization: None. The skill performs no validation, filtering, or escaping of the user-provided text before it is inserted into the sub-agent's execution context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:49 PM
Security Audit — agent-trust-hub — specialist-engineering-senior-developer