seo-expert
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is primarily a collection of expert SEO guidelines and markdown templates. Analysis of all files, including the Node.js test scripts, reveals no evidence of malicious intent, obfuscation, or data exfiltration.
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection due to its core functionality of auditing and analyzing untrusted data from external websites. 1. Ingestion points: Data is ingested through templates in files such as audit-global.md, analyse-concurrentielle.md, and ai-overviews.md which process external URLs and content. 2. Boundary markers: While data is structured using Markdown, the templates lack explicit delimiters or instructions to prevent the agent from obeying embedded directives in the audited content. 3. Capability inventory: The skill defines instructions for an LLM but does not contain autonomous scripts for network or filesystem access. 4. Sanitization: No specific mechanisms for sanitizing or escaping ingested web content are defined within the prompt templates.
Audit Metadata