programmatic-seo
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of untrusted external data.
- Ingestion points: The skill retrieves content using browser tools (Browser MCP, agent-browser) and reads user-provided data from external URLs and local files like .seo-context.md.
- Boundary markers: The instructions do not define explicit delimiters or warnings to ignore instructions that might be embedded within the external content retrieved.
- Capability inventory: The skill allows the agent to edit code and modify the filesystem when implementation is requested.
- Sanitization: No evidence of input validation or sanitization of data retrieved from external sources is provided.
Audit Metadata