expansion-discovery
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and structured templates for managing customer relationships. There are no scripts, binaries, or automated tool invocations.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define an attack surface by reading external data, but there is no mechanism for exploitation. 1. Ingestion points: The skill reads call notes, emails, and product usage data as described in SKILL.md Step 2. 2. Boundary markers: No specific delimiters or boundary instructions are included. 3. Capability inventory: No code, network access, or file-writing tools are included in the skill. 4. Sanitization: No sanitization logic is present as the skill is purely instructional.
Audit Metadata