seo-content
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (brand_context.py) located in the
${CLAUDE_SKILL_DIR}/../start-here/scripts/directory to load marketing and brand configuration. - [EXTERNAL_DOWNLOADS]: Performs network operations to fetch and scrape content from external organic search URLs and AI Overviews using the Firecrawl API or the WebFetch tool.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Processes untrusted data from live search engine results pages (SERPs) and third-party competitor websites during Phase 1 (SERP Reality) and Phase 1.5 (AI Surface Analysis).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore potential malicious prompts embedded in the scraped competitor content before it is used to draft the article.
- Capability inventory: The skill possesses file-write capabilities (saving content to
./campaigns/content/) and local command execution capabilities. - Sanitization: No sanitization or filtering is applied to the externally retrieved content.
Audit Metadata