proxelar

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow can ingest outsider-authored free text because Proxelar MITMs and logs/transforms HTTP request/response bodies from arbitrary external sites/apps (e.g., via --script .../log_to_jsonl.lua writing request.body/response.body into JSONL that is then available to the agent), which originates from parties the operating user did not author.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill instructs adding a CA cert to the system trust store using a sudo command ("sudo security add-trusted-cert ... /Library/Keychains/System.keychain"), which requires elevated privileges and modifies system-level security settings.