speckit-analyze

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly reads .specify/extensions.yml and then emits hook fields (command, prompt, EXECUTE_COMMAND) verbatim in its outputs, which would force the LLM to reproduce any embedded secrets (API keys, tokens, or credentials) found in those hook entries.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill specification instructs automatic execution of commands sourced from repository-controlled extension configs and a repo script, which enables arbitrary command execution (RCE) and can be abused for backdoor activity or data exfiltration.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.90). The skill instructs the agent to execute repository-defined extension hooks (mandatory pre- and post-hooks) and to run a repo script from the project root, which can run arbitrary commands that alter system state or require elevated privileges.