seo-content
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions (SKILL.md and human-checkpoint-guide.md). It does not include any Python, Node.js, or shell scripts, eliminating the risk of direct code-based attacks or malicious execution.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it requires the agent to analyze external web content (SERP analysis) and competitor URLs. However, this is inherent to the SEO purpose and mitigated by the structured 'Human Checkpoint' requirement.
- Ingestion points: Competitor URLs, search engine results, and existing web content provided for refreshing.
- Boundary markers: None explicitly defined in the prompt templates.
- Capability inventory: The agent is directed to read from and write to the local 'brand-memory/' directory and project folders.
- Sanitization: No explicit sanitization of ingested content is described in the logic.
Audit Metadata