seo-research
Warn
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: MEDIUMCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill documentation explicitly identifies the filesystem paths for sensitive authentication data, including an environment file (
.env) and a Google Cloud service account key (ga4-credentials.json) within theStudio/SEO Article Factory/credentials/directory. Disclosing these specific locations increases the risk of credential exposure if the agent's environment is accessed or compromised.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze data from external and potentially untrusted sources to perform keyword validation and competitive analysis. - Ingestion points: External DataForSEO API responses, competitor website content (SERP analysis), and local content archives including podcast transcripts and newsletter issues.
- Boundary markers: The instructions do not define clear delimiters or boundary markers to distinguish untrusted external content from system instructions.
- Capability inventory: The skill uses ingested data to perform scoring and generate structured research briefs that influence subsequent writing tasks.
- Sanitization: There is no mention of sanitization, filtering, or validation of the external content before it is processed by the agent.
Audit Metadata