lead-triage-form-fill
Fail
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: CRITICAL
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from lead forms (form submissions and contact emails) to generate triage recommendations. Ingestion points: SKILL.md (Workflow Step 1). Boundary markers: No specific delimiters or isolation instructions are provided. Capability inventory: No subprocess calls, exec/eval, file-write, or network operations are present. Sanitization: No explicit validation or filtering is defined. The risk is mitigated by the 'read-first' nature of the skill, which only proposes drafts for human review.
- [SAFE]: The author metadata identifies 'Builder.org'. While an external scanner flagged this domain, the skill contains no functional instructions or code that interact with the domain or perform any external network requests.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata