harness-triage

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

• Third-party content exposure detected (high risk: 0.85). Runtime path: the skill queries the GitHub issue tracker and “reads the full issue (body, comments, labels, reporter…)” (and prior triage notes) before generating recommendations, so outsider-authored issue/comment text can be ingested into the agent LLM context.

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

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