competitor-intel-agent
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches content from external, untrusted websites (competitor pages, job boards, blogs) via
WebFetchandWebSearch. This creates a surface for indirect prompt injection where malicious instructions hidden on those pages could influence the agent's behavior. - Ingestion points: Data is ingested from external URLs in
references/monitoring-dimensions.mdusingWebFetchandWebSearch. - Boundary markers: The skill instructions lack explicit boundary markers or instructions to isolate external content from system prompts.
- Capability inventory: The skill is granted access to
Bash,Write, andWebFetchtools, which defines the scope of potential impact from an injection. - Sanitization: No explicit sanitization or validation of the fetched content is described before processing.
Audit Metadata