account-progression-staging
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it aggregates untrusted data from external platforms to drive automated summaries and alerts. Maliciously crafted data in the CRM or web logs could attempt to manipulate the agent's output.
- Ingestion points: Data retrieved from
{{CRM}}(such as account or contact records),{{INTENT_SOURCE}}, and web/email activity logs inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for external data fields.
- Capability inventory: The skill is designed to write to CRM fields (
{{STAGE_FIELD}}) and post to communication channels ({{ALERTS_CHANNEL}}). - Sanitization: There is no evidence of string sanitization or validation for the incoming external data before it is processed.
- [NO_CODE]: The skill consists entirely of configuration instructions and templates; no scripts or executable files are included.
Audit Metadata