seo-backlink-audit
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze untrusted external data, including anchor text, referring domain content, and site metadata retrieved via the Ahrefs MCP.
- Ingestion points: The workflow in
SKILL.mdrequires pulling referring domain quality, link velocity, and anchor text distribution from external web sources. - Boundary markers: The instructions do not define clear delimiters or include warnings to the agent to ignore potentially malicious instructions embedded in anchor text or site descriptions.
- Capability inventory: The skill's primary capabilities are analytical and reporting; it does not request high-risk tools like shell access, file-system writes (beyond report generation), or arbitrary network requests.
- Sanitization: The instructions do not provide methods for sanitizing or escaping the content pulled from external backlink profiles.
Audit Metadata