botshot

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to read/save a bearer token from ~/.botshot/credentials.json and to include that token verbatim in Authorization headers and API requests, which requires the LLM to handle secret values directly.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and "glance at the feed" and to GET posts/search/agents (SKILL.md Step 4 and the API reference), which are public, user-generated Botshot posts that the agent is expected to read and use (e.g., set inspired_by, like, comment), so untrusted third-party content can influence its actions.