The Agent Skills Directory

[SAFE]: No evidence of prompt injection, data exfiltration, or malicious intent was found. The skill's behavior is consistent with its stated purpose of forecast tracking and scoring.
[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (ledger.py) to manage the forecast ledger. This execution is confined to the local environment and is necessary for the skill's primary functionality.
[PROMPT_INJECTION]: While the skill ingests external data (forecast questions and notes), it does so for storage and display purposes. No evidence of malicious interpolation or instruction override was detected.

forecast-ledger