seo-specialist
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from user-provided URLs and competitor websites, which introduces a surface for indirect prompt injection.\n
- Ingestion points: The agent ingests external data through the
/seo-specialist audit <URL>command and the 'Competitor URLs' context gathering step defined in Step 1 of the skill workflow.\n - Boundary markers: The skill's instructions do not include explicit delimiters or instructions to the agent to treat external content as data only or to ignore instructions embedded within audited pages.\n
- Capability inventory: The agent is instructed to generate and save output as local markdown files (
seo-brief-*.md), which could potentially store malicious content if an injection occurred during an audit.\n - Sanitization: The skill lacks logic to sanitize or filter potentially malicious instructions embedded in the external pages it analyzes.
Audit Metadata