audience-profile
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted customer data, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads customer data supplied through surveys, CRM exports, and analytics demographics as described in the process section of SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between data and potential commands within the ingested content.
- Capability inventory: The skill is capable of reading local configuration files from the ~/.claude-marketing/ directory but lacks network or command execution capabilities in the provided definitions.
- Sanitization: No evidence of sanitization, filtering, or validation is present for the data read by the skill.
Audit Metadata