keyword-research
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, including customer support tickets, sales calls, reviews, and competitor website content. While this introduces a surface for indirect prompt injection, the skill lacks dangerous capabilities such as arbitrary code execution, file system modifications, or automated network exfiltration, which significantly limits the potential impact.
- Ingestion points: Customer language sources (support tickets, reviews) and competitor website data specified in the 'Intake' section.
- Boundary markers: No specific delimiters or safety instructions are defined for processing the external intake data.
- Capability inventory: The skill is limited to generating a text-based keyword map and does not utilize subprocesses, file writes, or network operations.
- Sanitization: No explicit sanitization or validation of the external content is performed.
- [SAFE]: The skill follows standard marketing workflows and does not contain any detected malicious patterns, persistence mechanisms, or unauthorized privilege escalation attempts.
Audit Metadata