outbound-analyst
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data from potentially untrusted sources, which creates a surface for indirect prompt injection.
- Ingestion points: In
SKILL.md, the instructions prompt the agent to process "campaign exports, platform access, a dashboard" and to evaluate "real replies from the conversations or inbox". - Boundary markers: The instructions do not specify the use of delimiters or provide warnings for the agent to ignore instructions that may be hidden within the ingested sales data or message content.
- Capability inventory: The skill itself does not define dangerous capabilities such as file system writing, network requests to external domains, or execution of arbitrary shell commands.
- Sanitization: There is no evidence of input validation or sanitization routines for the external data being analyzed.
Audit Metadata