seo-context
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from multiple external project files, which could contain instructions that influence the agent's behavior.\n
- Ingestion points: The workflow instructs the agent to read repository content such as
README.md, strategy notes, and product/marketing documentation to extract SEO-related facts.\n - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill to protect against malicious content in the ingested files.\n
- Capability inventory: The skill has the capability to read project files, write to the
.seo-context.mdfile, and inspect the inventory of available agent tools and connectors.\n - Sanitization: There is no requirement for the agent to sanitize or validate the content extracted from external documents before recording it in the shared context file.
Audit Metadata