aeo-setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly tells the agent to ask the user for API keys and then write them into .env via echo commands (e.g., echo 'GOOSE_AEO_PERPLEXITY_API_KEY=...'), which requires the LLM to include secret values verbatim in its generated output.

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md Step 3 explicitly says the tool will "auto-discover" competitors using Perplexity (if the API key is set) and the agent parses that JSON output to set competitors/providers, so it consumes and acts on untrusted third‑party search results.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill invokes the external package via runtime commands like "npx goose-aeo init" and the README points to the repository https://github.com/athina-ai/goose-aeo, so this external package/repo is a required runtime dependency that would be fetched/executed and can directly control prompt generation and agent behavior.