github-archive

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow queries GitHub Archive BigQuery tables and ingests event payload fields (including issue/PR bodies and comments) authored by third parties, which are outsider-authored free text that can be extracted into the agent’s LLM context via query results.

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

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