multi-channel-outreach
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides strategic outbound sales guidance and templates for multi-channel communication. No malicious behaviors, exfiltration attempts, or unauthorized access patterns were identified across the documentation or scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection as it ingests user requirements to generate outreach sequences and uses a script (
scripts/check-output.py) to validate the generated files. However, the validation script's logic is highly restricted, performing only benign keyword and length checks without displaying file content or executing instructions, which mitigates any practical risk. - Ingestion points: User-provided outreach requirements in
SKILL.md. - Boundary markers: Not explicitly used in the output templates.
- Capability inventory: Local file read access via
scripts/check-output.py. - Sanitization: Not present in the sequence templates.
- [EXTERNAL_DOWNLOADS]: The skill references established sales methodologies and platforms such as Saleshandy, Reply.io, and lemlist. These references are provided for informational context and do not involve downloading or executing untrusted code or scripts from external sources.
Audit Metadata