The Agent Skills Directory

[SAFE]: The skill consists of pedagogical instructions and content templates for SEO auditing. No malicious code, obfuscation, or unauthorized network operations were detected.
[DATA_EXPOSURE]: The skill instructs the agent to read .claude/product-marketing-context.md if it exists. This is a local file access intended for project-specific context and does not constitute a security risk in this implementation.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by reading external context files, which could theoretically contain instructions. However, the risk is negligible as the skill lacks high-privilege capabilities such as shell execution or network access.
Ingestion points: .claude/product-marketing-context.md (referenced in SKILL.md)
Boundary markers: Absent
Capability inventory: No subprocess calls, file-write, or network operations detected across scripts.
Sanitization: Absent

seo-audit