campaign-sending
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill transmits lead data, including email addresses and personalization fields, to the Instantly.ai API (api.instantly.ai). This is the primary functionality for campaign management.
- [EXTERNAL_DOWNLOADS]: The workflow involves fetching API documentation from external web sources if the provider is not already configured in the local references directory.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external data from lead CSV files and remote API documentation.
- Ingestion points: Lead data CSV files and dynamically fetched provider documentation (SKILL.md).
- Boundary markers: There are no explicit markers or instructions to isolate or ignore potential commands within the lead data or documentation.
- Capability inventory: The skill can perform network requests to third-party APIs and read local file contents (SKILL.md, references/instantly-api.md).
- Sanitization: No explicit validation or sanitization is performed on the contents of the CSV or fetched documentation.
Audit Metadata