comparison-pages
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows standard instructional patterns for content generation and includes a local validation script,
comparison-check.js, which does not perform any network operations, file system modifications, or sensitive data access. - [SAFE]: All external links point to reputable sources such as official government regulations (16 CFR 14.15) and well-known documentation platforms (Google Search Central).
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content (competitor facts and marketing copy) through its validation tool. However, the script is a pure text processor without capabilities for network exfiltration or command execution, neutralizing the risk of indirect injection.
- Ingestion points: User-supplied JSON configuration passed to
node resources/comparison-check.js(SKILL.md). - Boundary markers: Not explicitly defined in the script output.
- Capability inventory: No file writes, no network operations, and no subprocess calls are performed by the validator script.
- Sanitization: The script performs regex-based scanning for specific keywords but does not sanitize content for LLM instructions.
Audit Metadata