obsidian-mind
Warn
Audited by Snyk on Jul 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Required runtime workflow ingests outsider-authored free text when an outside user supplies messages/recaps (via the consuming agent chat or
/om-dump) that are handled by theUserPromptSubmithook for classification/routing and then written/validated byPostToolUse, so attacker text can flow into the LLM without first selecting a specific item.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs fetching and updating the vault from the upstream repository (e.g., "shardmind install github:breferrari/obsidian-mind" and "Update this vault ... https://github.com/breferrari/obsidian-mind" and references the raw README at https://raw.githubusercontent.com/breferrari/obsidian-mind/main/README.md), which is used at install/update/runtime to pull repository files (CLAUDE.md, hooks, scripts) that directly control agent prompts and behavior.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata