sharemd

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill shows an API key embedded in a shell command and explicitly instructs the agent to "pass through" and "report" user passwords verbatim, which requires the LLM to include secret values in calls/outputs.

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

• Third-party content exposure detected (medium risk: 0.30). The ShareMD skill reads markdown provided in the user’s conversation or a user-specified file path (“turn markdown from the conversation into a public link”), which is outsider-authored free text ingested at runtime before the skill selects what to share.