football-data
Warn
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's setup instructions in SKILL.md require installing the 'sports-skills' package from PyPI or directly from a GitHub repository (github.com/machina-sports/sports-skills.git), which is not a trusted vendor.
- [REMOTE_CODE_EXECUTION]: The instruction to use 'pip install git+' allows for the execution of arbitrary code from a remote repository during the setup phase of the skill.
- [COMMAND_EXECUTION]: The skill primarily functions by executing a CLI tool ('sports-skills'), which represents a capability that could be misused if the tool itself is compromised or handles malicious input from the sports data sources.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its ingestion of untrusted external data. Ingestion points: The skill fetches match summaries, stats, and player profiles from external websites like ESPN, Understat, FPL, and Transfermarkt. Boundary markers: Absent; no instructions are provided to the agent to treat this external content as untrusted or to ignore embedded commands. Capability inventory: The skill performs subprocess execution through the 'sports-skills' CLI as mentioned in SKILL.md. Sanitization: Absent; the skill lacks validation or filtering for data retrieved from external sports data providers.
Audit Metadata