log-analysis

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md explicitly states the skill “processes user-supplied content” such as raw log data/event payloads/SIEM query results, which at runtime can include outsider-authored free text (e.g., log entries/comments from other parties) that the agent then reads into its LLM context for analysis.