business-analyst

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection via external data ingestion.
  • Ingestion points: The instructions in SKILL.md specifically direct the agent to 'Review existing documentation, data sources, and stakeholder needs' and 'Query context manager for business objectives'.
  • Boundary markers: There are no boundary markers, delimiters, or explicit instructions provided to the agent to disregard or isolate embedded commands found within the processed external documents.
  • Capability inventory: The skill contains no active code execution capabilities, network operations, or file-writing scripts, which significantly mitigates the risk of an injection being escalated.
  • Sanitization: No input validation or content filtering mechanisms are defined for the data processed by the agent.
  • [NO_CODE]: The skill is composed entirely of natural language prompt instructions and YAML metadata with no accompanying executable scripts or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:37 AM