competitive-positioning
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external and untrusted sources, which creates a surface for indirect prompt injection attacks.
- Ingestion points: The skill reads from customer calls, CRM transcripts, support logs, third-party reviews, and community sentiment as described in references/CONTEXT.md and references/INTERNAL.md.
- Boundary markers: The skill instructions do not explicitly define delimiters or 'ignore instructions' warnings for processed data to isolate external content from the system instructions.
- Capability inventory: The skill utilizes read-only market intelligence tools and internal data connectors. It lacks dangerous capabilities such as arbitrary command execution, file system writes, or direct network requests to unverified domains.
- Sanitization: There are no explicit sanitization or filtering steps defined for the external content before it is processed by the agent.
Audit Metadata