appendices

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to its core logic of aggregating data from various user-controlled business plan sections.
  • Ingestion points: Sections 01-14 of the business plan are explicitly identified as data sources in SKILL.md.
  • Boundary markers: The skill does not define delimiters or provide instructions to the agent to treat ingested data as non-executable text, creating a risk that malicious instructions in the business plan could influence agent behavior.
  • Capability inventory: The agent is tasked with generating complex documents, financial tables, and structured appendices based on the untrusted input.
  • Sanitization: No sanitization, validation, or escaping logic is included to protect against adversarial content within the ingested sections.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 01:40 AM