seo-content-brief
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external web searches and API responses to generate content outlines. This allows for a potential attack vector where malicious data on the web could influence the agent's instructions.
- Ingestion points: Web search results and data retrieved from the Semrush API in SKILL.md.
- Boundary markers: None provided to distinguish between instructions and ingested data.
- Capability inventory: Tool usage (WebSearch) and network data retrieval (curl). The skill does not possess capabilities for file writing or system modification.
- Sanitization: There is no evidence of filtering or sanitizing the data fetched from the web.
- [DATA_EXFILTRATION]: The skill utilizes
curlto communicate with the Semrush API (api.semrush.com). This network operation is used to retrieve keyword metrics and does not involve the transmission of sensitive system files or credentials. As a well-known service in the SEO industry, this usage is consistent with the skill's stated purpose.
Audit Metadata