seo-automation
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for auditing and crawling external websites and competitor domains. This creates an attack surface where malicious content on a target site could attempt to influence the agent's behavior through hidden instructions. 1. Ingestion points: User-provided website URLs, competitor domains, and external SEO tool data (SKILL.md). 2. Boundary markers: None specified to delineate between system instructions and processed web content. 3. Capability inventory: Extensive analysis, keyword scoring, and pipeline generation tasks; no direct shell or file-writing scripts are present. 4. Sanitization: No sanitization or filtering of the content retrieved from target domains is mentioned.
- [NO_CODE]: The skill contains only instructional markdown and frontmatter metadata; no scripts (e.g., Python, JavaScript, Bash) or executable binary files are included in the package.
Audit Metadata