nginx-docs
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface through the ingestion of external documentation content. * Ingestion points: External documentation pages from nginx.org and user-provided configuration snippets. * Boundary markers: The skill does not define specific delimiters for separating user queries or external documentation text. * Capability inventory: No scripts, subprocess calls, or system-level write operations are present in the skill files. * Sanitization: No explicit content sanitization logic is provided.
- [EXTERNAL_DOWNLOADS]: The skill provides numerous references to external documentation on the official nginx.org domain in SKILL.md and references/topic-map.md. These links are intended for information retrieval and grounding, which is consistent with the skill's primary purpose as a documentation assistant.
Audit Metadata