seo-content-brief
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data including 'current_page_html_or_text' and 'target_query_or_topic' without specifying boundary markers or instructions to ignore potential commands embedded in that data.\n
- Ingestion points: The 'contract.yaml' file defines 'target_query_or_topic', 'current_page_html_or_text', 'competitors', and 'customer_questions' as external data inputs.\n
- Boundary markers: There are no explicit delimiters (like XML tags or triple quotes) or 'ignore' instructions used when interpolating these inputs into the prompt.\n
- Capability inventory: Based on 'SKILL.md' and 'contract.yaml', the skill only performs text analysis and generation; it does not utilize tools for file system writing, network requests, or shell command execution.\n
- Sanitization: No sanitization, escaping, or filtering of the external content is mentioned or implemented.
Audit Metadata