lead-qualifier
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes inbound lead messages which originate from external, untrusted third parties, creating a potential vector for indirect prompt injection.
- Ingestion points: The instructions in SKILL.md ask users to paste untrusted content (emails, DMs) into the agent's prompt context.
- Boundary markers: The prompt template lacks strong delimiters or explicit instructions for the agent to treat the pasted content strictly as data and to ignore any embedded commands.
- Capability inventory: The skill is configured for text analysis and scoring; it does not explicitly define tool usage or file system access in the provided instructions.
- Sanitization: The skill does not implement sanitization or pre-processing to strip potential malicious instructions from the lead messages.
Audit Metadata