seo-copywriting
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs web searches to analyze competitor content and SERP features (Step 2: SERP Analysis). This creates a vulnerability to indirect prompt injection where malicious instructions could be embedded in external web pages.
- Ingestion points: External web content fetched during SERP analysis and competitor gap identification (SKILL.md, Step 2).
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands when processing external site data.
- Capability inventory: The skill possesses web search (read), file system access (read/write references), and content generation capabilities.
- Sanitization: No evidence of sanitization or filtering of external content before processing is present.
- [DYNAMIC_EXECUTION]: The skill instructs the agent to execute a local Python script as part of its auditing process.
- Evidence: The "Post-Publish Audit Loop" section explicitly mentions running
link_cluster_validator.py(project-local) to verify product-to-article linkages.
Audit Metadata