mattermost
Warn
Audited by Snyk on Mar 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and interacts with Mattermost content (channels/posts) via Membrane actions and the proxy request flow (see SKILL.md references to "Channel -> Post",
membrane action run, andmembrane request CONNECTION_ID /path/to/endpoint), which exposes the agent to user-generated, third-party messages that could contain instructions influencing agent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata