specialist-data-data-consolidation-agent

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses the {the user's question} placeholder directly within the sub-agent prompt. This allows untrusted user input to flow into the instruction context of a specialized agent, which is a common vector for manipulation or instruction override.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
  • Ingestion points: User input enters the agent context via the {the user's question} placeholder in SKILL.md within the Agent tool call.
  • Boundary markers: Absent. The user input is appended at the end of the prompt without delimiters or instructions for the agent to treat it as data rather than instructions.
  • Capability inventory: The specialist agent is empowered to consolidate data from CRM systems, API feeds, and spreadsheets, representing access to potentially sensitive corporate data.
  • Sanitization: There is no evidence of input sanitization, filtering, or validation before interpolating the user's question into the sub-agent's prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:49 PM
Security Audit — agent-trust-hub — specialist-data-data-consolidation-agent