mattermost

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill shows an explicit insecure pattern—using mm login --token YOUR_TOKEN—which instructs embedding a personal access token on the command line and would require the agent to include secret values verbatim in generated commands.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads user-generated Mattermost chat content from a Mattermost server using the mm CLI (e.g., mm messages, mm thread, mm search, as documented in SKILL.md and references/scenarios.md), which the agent is expected to read and summarize or use to draft replies, so untrusted third‑party messages could inject instructions.