seo-content-brief
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of content from external websites to analyze SERP results and competitor data.\n
- Ingestion points: Content extracted from URLs via the
tavily/extracttool.\n - Boundary markers: No explicit delimiters or warnings are provided to the agent to ignore potentially malicious instructions embedded in the analyzed web content.\n
- Capability inventory: The agent can execute shell commands via the
beltCLI and perform network searches.\n - Sanitization: There is no evidence of sanitization or filtering applied to the data retrieved from external sources before processing.\n- [EXTERNAL_DOWNLOADS]: The documentation includes instructions to download and install external tools and additional agent skills.\n
- Evidence: The skill references
npx skills add belt-sh/cliandnpx skills add inference-sh/skills@seo.\n - Context: These downloads target repositories managed by the skill's author and are integral to the stated purpose of the skill.
Audit Metadata