ai-seo
Warn
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides setup instructions that include cloning an external repository from an untrusted source (https://github.com/AminForou/mcp-gsc) and installing dependencies using pip install.
- [COMMAND_EXECUTION]: The GSC MCP configuration requires running a Python script (server.py) from the downloaded third-party repository within the agent's environment.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. 1. Ingestion points: The skill ingests untrusted competitor reviews and pain points from third-party sites like G2 and Capterra (SKILL.md). 2. Boundary markers: No delimiters or instructions to ignore embedded commands are present in SKILL.md. 3. Capability inventory: The skill uses AirOps workflows to push content to external CMS platforms like WordPress and Webflow via API (SKILL.md). 4. Sanitization: No sanitization or filtering of external data is specified.
Audit Metadata