cmd-speckit-converge

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt requires reading .specify/extensions.yml and emitting/printing hook command strings (and an EXECUTE_COMMAND block) and then invoking them; if those commands contain API keys, tokens, or other secrets the agent will output them verbatim, creating a high exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill explicitly requires reading and executing arbitrary hook commands from a repository-controlled YAML and running an arbitrary repo script, which enables remote code execution and easy data exfiltration / supply-chain backdoors.