negative-keyword-miner
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate workflows for Google Ads and Microsoft Ads management. All analyzed logic and documentation are consistent with the stated purpose of keyword mining and efficiency analysis.
- [NO_CODE]: The skill does not include any executable scripts, binaries, or shell commands. It relies entirely on SQL templates (GAQL) and natural language instructions for the agent to execute within its operational environment.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and analyzing untrusted search term data, which constitutes a potential injection surface.
- Ingestion points: Search term reports retrieved via GAQL queries in SKILL.md.
- Boundary markers: Absent; the instructions do not specify the use of delimiters or isolation protocols for search term content during analysis.
- Capability inventory: The skill is strictly limited to data analysis and categorization; it contains no capabilities for file system modification, network exfiltration, or subprocess execution that could be exploited.
- Sanitization: Absent; no explicit filtering or escaping of search term content is defined in the workflow.
Audit Metadata