setup-outreach-campaign
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from lead lists (CSV or upstream JSON) which is then interpolated into prompts for generating email sequences, creating a surface for indirect instructions.
- Ingestion points: The skill reads user-provided CSV files or JSON data from upstream skills to populate campaign leads (
SKILL.md, Step 4a). - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded within the lead data fields (e.g., in a 'title' or 'company' field).
- Capability inventory: The skill possesses file read capabilities and network write access to the Smartlead API (
server.smartlead.ai). - Sanitization: While the skill validates email formats and performs deduplication, it does not specify sanitization or escaping for the content fields used in email body generation.
Audit Metadata