football-data

Fail

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation instructs the user to install the sports-skills package from PyPI or GitHub. The repository https://github.com/machina-sports/sports-skills.git is not associated with a trusted organization or well-known service.\n- [REMOTE_CODE_EXECUTION]: Installing a package directly from a git repository using pip install git+ allows for the execution of arbitrary code during the installation process via setup.py or other installation hooks.\n- [COMMAND_EXECUTION]: The skill relies on the sports-skills CLI for its primary functionality and executes a local shell script scripts/validate_params.sh for parameter validation. These operations involve system-level command execution.\n- [PROMPT_INJECTION]: The skill ingests user-provided strings such as team names and event IDs (e.g., in the search_team query) and incorporates them into command-line executions. Lack of comprehensive sanitization (only season_id is validated in scripts/validate_params.sh) creates an attack surface for indirect prompt injection or command injection. The ingestion points include the query and event_id parameters in SKILL.md, while the capability inventory includes CLI calls to the sports-skills tool.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 13, 2026, 06:59 AM