seo-local
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingest content from external URLs provided by the user for analysis. This creates a theoretical surface for indirect prompt injection if an analyzed page contains malicious instructions designed to influence the agent's behavior. However, this risk is inherent to the primary purpose of an SEO auditing tool.
- Ingestion points: Fetches content from external websites via user-provided URLs and reads local context from the
.seo-cache/directory. - Boundary markers: No specific delimiters or "ignore embedded instructions" directives are present in the prompt to separate external content from agent instructions.
- Capability inventory: The skill performs file read/write operations within the project directory for caching and utilizes standard web fetching and search tools.
- Sanitization: No explicit sanitization or filtering of external content is defined before the agent processes the information for the audit.
- [DATA_EXPOSURE]: The skill reads from and writes to a local
.seo-cache/directory to maintain context between different SEO audit stages. This is a standard optimization practice and does not involve accessing sensitive user credentials or system files.
Audit Metadata