gtm-audit
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data from multiple sources to perform its audit.
- Ingestion points: Data enters the agent's context through website content, LinkedIn profiles, CRM exports, and call notes provided as evidence in
SKILL.md. - Boundary markers: The instructions lack specific delimiters (e.g., XML tags or triple quotes) or 'ignore' instructions to prevent the agent from obeying commands embedded within the analyzed evidence.
- Capability inventory: The skill has report generation capabilities; no high-risk capabilities like remote command execution or network exfiltration were detected.
- Sanitization: There are no defined mechanisms for sanitizing or validating the external content before it is processed by the agent.
Audit Metadata