honeybadger

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to ask the user to paste their personal API token and then include that token verbatim in a command-line invocation (ruby .../save_token.rb 'PASTED_TOKEN'), which exposes the secret in the agent's output/context.

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

• Third-party content exposure detected (high risk: 0.70). Yes — the skill makes authenticated API calls to the public Honeybadger service (BASE_URL https://app.honeybadger.io/v2 in scripts/auth.rb) and several runtime scripts (notably scripts/fault.rb and scripts/faults.rb) fetch and print fault and notice messages (user-generated/untrusted content) which the agent is expected to read and present as part of its workflow, so those third-party messages could materially influence decisions or next actions.