geo-content-planning
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for data transformation and clustering using provided CSV and Markdown files. It does not utilize any platform tools, network capabilities, or shell access.
- [SAFE]: No patterns of prompt injection, obfuscation, or persistence were detected in the instructions or schema.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external CSV files, which represents an attack surface. However, this is categorized as safe because the skill possesses no capabilities that could be exploited via injected instructions. * Ingestion points: Content is read from keywords.csv and prompts.csv (referenced in SKILL.md). * Boundary markers: No explicit delimiters are present to separate instructions from data. * Capability inventory: No tools, subprocesses, or network operations are enabled. * Sanitization: Input data is processed as raw text without specific filtering.
Audit Metadata