speckit-initial

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt explicitly references passing a GitHub token via a command-line flag (--github-token ) and suggests setting GITHUB_TOKEN, which can cause the agent to include secret values verbatim in generated commands or code (direct CLI flags are high-risk for secret exfiltration).

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The runtime workflow runs specify init, which pulls the .specify/ templates/memory/scripts/specs from the Spec Kit source (e.g., GitHub/public repo) and then registers slash commands; that fetched outsider-authored free text/templates would be ingested into the agent context via the installed project assets.