newsletter-curation
Fail
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- Remote Code Execution (HIGH): The skill instructs the user to run
curl -fsSL https://cli.inference.sh | sh. This is a high-risk 'piped to shell' pattern that executes unverified code from a non-trusted domain. - External Downloads (MEDIUM): The skill uses
npx skills addto install additional logic frominferencesh/skills, which is an untrusted registry according to the established trust scope. - Indirect Prompt Injection (LOW): The skill is designed to ingest and curate data from external search tools (
tavily/search-assistantandexa/search). Ingestion points: Search results are directly formatted into newsletter templates inSKILL.md. Boundary markers: The templates do not use delimiters or warnings to ignore embedded instructions in the search data. Capability inventory: The skill has access to shell commands viaBash(infsh *)and social media posting viax/post-create. Sanitization: No escaping or validation is performed on the ingested content.
Recommendations
- HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata