ai-seo
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to ingest data from external files that may contain untrusted user content, potentially influencing the agent's behavior during tool execution.\n
- Ingestion points: The agent is directed to read
.agents/marketing-strategy.mdand.agents/marketing-learnings.md(among other variants) at the start of the task inSKILL.md(lines 17-20).\n - Boundary markers: There are no instructions for the agent to use specific delimiters or to disregard instructions embedded within these external files.\n
- Capability inventory: The skill identifies integrations with tools such as
semrush,ahrefs,gsc, andga4in the tools registry for implementing SEO tasks (lines 485-492).\n - Sanitization: No sanitization or validation logic is provided to handle the content of the external files before the agent processes them.
Audit Metadata