seo-content
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted content from user-provided URLs and local cache files.
- Ingestion points: Content retrievable from external URLs and JSON data stored in the
.seo-cache/directory. - Boundary markers: The instructions do not define explicit delimiters or warnings to prevent the agent from following instructions embedded within the analyzed web content.
- Capability inventory: The skill performs file system read/write operations (for caching) and invokes external DataForSEO tools for keyword and sentiment analysis.
- Sanitization: No explicit sanitization or filtering of the ingested external content is mentioned.
- [COMMAND_EXECUTION]: The skill performs file system operations to manage its local data cache in
.seo-cache/, including reading site metadata and writing audit summaries. This is localized to the project directory and follows standard caching practices.
Audit Metadata