Proposal Generator

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is vulnerable to instructions embedded in external data it is designed to ingest (such as email threads or call transcripts), which could attempt to override the agent's behavior during the proposal generation process.
  • Ingestion points: Intelligence is gathered from Call History, Email Threads, and CRM Data as specified in SKILL.md.
  • Boundary markers: The skill lacks explicit delimiters or instructions to disregard potential commands found within the ingested source material.
  • Capability inventory: The skill relies on web_search and implied tools for searching internal databases and communication history.
  • Sanitization: No instructions are provided to sanitize or validate the content of the retrieved data before it is interpolated into the proposal document.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:38 AM