gips-compliance

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process and analyze financial performance data, which often originates from untrusted external sources (e.g., firm reports, client portfolios). This creates a risk of indirect prompt injection, where malicious instructions hidden in data could manipulate the agent.
  • Ingestion points: Performance data, composite definitions, and compliance documents processed during tasks like 'reviewing composites' or 'calculating returns' (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided for data ingestion.
  • Capability inventory: The skill allows access to high-privilege tools including 'Bash', 'Write', and 'Edit' (SKILL.md).
  • Sanitization: The skill lacks defined validation or sanitization procedures for data extracted from external documents before it is used in prompt contexts or tool execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 06:57 AM