football-data
Fail
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository
https://github.com/machina-sports/sports-skills.gitfor package installation, which is not included in the trusted vendors list.- [REMOTE_CODE_EXECUTION]: The setup instructions utilizepip installto download and install code from a remote Git repository. This allows the execution of unverified external code within the agent's environment.- [COMMAND_EXECUTION]: The skill relies on executing thesports-skillsCLI tool to perform various football data retrieval tasks.- [PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection. - Ingestion points: Data is ingested from multiple external sources including ESPN, Understat, FPL, and Transfermarkt via the
sports-skillstool (e.g., inget_daily_scheduleandget_event_summary). - Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: The skill possesses the capability to execute shell commands via the
sports-skillsCLI tool as demonstrated inSKILL.mdandscripts/validate_params.sh. - Sanitization: Absent; no validation or filtering is applied to the ingested external content to prevent malicious instructions from influencing the agent.
Recommendations
- AI detected serious security threats
Audit Metadata