openclaw-secret-scanning-maintainer

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

• Third-party content exposure detected (high risk: 0.95). The workflow fetches GitHub Secret Scanning alert content at runtime via fetch-content (saving body_file from the alert’s location-json), which is outsider-authored free text (issue/PR bodies and comments by other users) that the agent then reads to identify and redact secrets.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)