cold-outreach
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of documentation and evaluation configuration. No executable scripts (Python, JavaScript, Shell) or binary payloads are present within the provided files or the skill archive.
- [SAFE]: The instructions focus on legitimate technical setup for email deliverability, including SPF, DKIM, and DMARC configurations, as well as domain warmup strategies. All mentioned domains and tools are standard industry services.
- [INDIRECT_PROMPT_INJECTION]: The skill describes personalizing outreach based on external data. 1. Ingestion points: Company news and podcast mentions described in the strategy. 2. Boundary markers: None specified. 3. Capability inventory: None (no executable code). 4. Sanitization: None specified. The risk is safe as the skill is purely informational guidance.
Audit Metadata