heyreach-connect
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (SAFE): No patterns detected that attempt to override agent instructions or bypass safety filters.
- Data Exposure & Exfiltration (SAFE): API keys are managed through user input and local .env files, which is a standard configuration practice. No unauthorized access to existing sensitive files was detected.
- Unverifiable Dependencies (SAFE): The skill relies on local scripts within a specific system path. No remote scripts or external packages are downloaded or executed.
- Indirect Prompt Injection (LOW): The skill ingests data from the external HeyReach API, which could potentially contain malicious instructions if the external data is compromised. * Ingestion points: API response data from scripts like list_campaigns.py and get_leads.py. * Boundary markers: None documented in the skill file. * Capability inventory: Multiple subprocess calls to local Python scripts. * Sanitization: No sanitization of external API data is described in the skill file.
Audit Metadata