The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were found in the skill's instructions or metadata.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or instructions to store credentials insecurely were detected.
[EXTERNAL_DOWNLOADS]: The skill does not perform any network operations or download external resources.
[COMMAND_EXECUTION]: Although 'bash' and 'python' are listed as allowed tools in the frontmatter, no malicious scripts or dangerous command execution patterns (like sudo or shell profile modifications) are present.
[DATA_EXFILTRATION]: No access to sensitive file paths (~/.ssh, ~/.aws, .env) or patterns of data exfiltration were found.
[REMOTE_CODE_EXECUTION]: No remote script execution (e.g., curl | bash) or dynamic code generation from untrusted sources was identified.
[SAFE]: The skill's primary function is to serve as a math assistant using its own internal reference documents, representing a low-risk use case.

math-helper