proof-kb
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to connect to external Model Context Protocol (MCP) services at
https://scribiz.com/mcpandhttps://aiseotracker.com/api/agent/mcp. It also suggests usingnpx scribiz, which downloads code from the npm registry at runtime. - [REMOTE_CODE_EXECUTION]: The workflow relies on the execution of external packages via
npxand interactions with third-party API services to perform video analysis and SEO tracking. - [COMMAND_EXECUTION]: The agent is instructed to use shell commands such as
grepto scan the repository for specific fact strings and IDs to maintain data consistency across multiple files. It also reads potentially sensitive files likepackage.json, database schemas, and incident postmortems to extract verifiable facts. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, specifically video recordings and transcripts via the Scribiz tool. This presents a surface for indirect prompt injection if the external content contains malicious instructions designed to influence the agent's behavior during the knowledge extraction process.
Audit Metadata