account-research
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Data Ingestion and Synthesis: The skill is designed to collect information from various sources including web searches, enrichment platforms, and CRM systems to generate sales intelligence. This data collection and synthesis is the primary function of the skill.
- Indirect Prompt Injection Surface: Because the skill processes content from external websites via search, it inherently possesses an indirect prompt injection surface where external data could attempt to influence the agent's output. This is a common characteristic of research-oriented AI skills.
- Ingestion points: Processes content from web search results (Step 2), enrichment tool outputs (Step 3), and CRM records (Step 4).
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore embedded prompts within the fetched data.
- Capability inventory: The skill relies on search tools and API connectors for data retrieval; it does not explicitly define file system writes or shell command execution within its instructions.
- Sanitization: No specific sanitization or filtering logic is described for the retrieved external content.
Audit Metadata