proposal-development

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data such as RFPs, conversation notes, and commercial inputs to produce business artifacts. This creates a vulnerability where instructions embedded in those documents could influence the agent's behavior. \n
  • Ingestion points: RFPs, notes, and commercial inputs provided by the user. \n
  • Boundary markers: The skill does not define delimiters or specific instructions to isolate or ignore embedded prompts in the source material. \n
  • Capability inventory: The agent uses file-writing and presentation tools to generate deliverables. \n
  • Sanitization: No sanitization or validation of the ingested content is instructed.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 05:06 AM