add-imessage

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks the agent to collect a secret API key and then inject it verbatim into a shell command (bash setup/... "{{api_key}}"), which requires the LLM to handle/output the secret directly and thus creates an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow ingests outsider-authored free text via user prompts/captures (mode, Photon server_url/api_key, owner_handle) that the agent processes into configuration and wiring logic, enabling indirect prompt-injection-style payloads from the user’s messages.