seo-seranking
Warn
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: MEDIUMINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from users (brand names, keywords, URLs) and external API responses from SE Ranking. 1. Ingestion points: Command parameters (brand, keyword, url) and data from the SE Ranking API. 2. Boundary markers: Absent; no delimiters are used to isolate external content. 3. Capability inventory: Execution of local scripts (install.sh, dataforseo_costs.py). 4. Sanitization: Absent; no validation or escaping of ingested content is specified.
- [DATA_EXFILTRATION]: The skill instructions require the agent to access and verify the content of ~/.claude/settings.json to check for the SERANKING_API_KEY. Accessing this file exposes sensitive platform settings and potentially other stored credentials to the agent environment.
- [COMMAND_EXECUTION]: The skill triggers the execution of local shell and PowerShell scripts (install.sh, install.ps1) and a cost-logging Python script via a custom command tool.
Audit Metadata