The Agent Skills Directory

[SAFE]: The skill's primary function is local documentation management. It reads and writes to HUMAN.md and HUMAN_FRICTIONS.md within the project repository to track workflow improvements.
[PROMPT_INJECTION]: No patterns indicative of prompt injection, such as instructions to ignore safety guidelines or bypass constraints, were detected in the instructions or the schema.
[REMOTE_CODE_EXECUTION]: The skill does not contain any patterns for downloading or executing remote code. It does not use package managers or dynamic execution functions like eval or exec.
[DATA_EXFILTRATION]: No network-related commands (e.g., curl, wget) or access to sensitive file paths (e.g., .ssh, .aws, .env) were found. The skill operates exclusively on project-specific feedback files.
[COMMAND_EXECUTION]: There is no evidence of shell command execution or attempts at privilege escalation. The skill limits its activities to structured text manipulation.

human-feedback