connector-slack
Fail
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the
slack-clientandcaffeineai-authorizationpackages from the Motoko Package Manager registry (mops.one). While an automated scanner flagged the registry URL as suspicious, it is the standard, well-known package registry for the Motoko ecosystem. - [INDIRECT_PROMPT_INJECTION]: The skill provides the capability to read content from Slack (e.g., channel history and replies), creating a surface for indirect prompt injection attacks.
- Ingestion points: API calls to
conversationsHistoryandconversationsRepliesas documented inSKILL.md. - Boundary markers: There are no explicit markers or developer instructions provided to distinguish between Slack message data and potential instructions to the agent.
- Capability inventory: The skill grants the agent extensive capabilities, including posting/editing messages, deleting files, and managing reactions.
- Sanitization: No sanitization or escaping of external Slack content is demonstrated in the provided Motoko snippets, meaning malicious content in a Slack message could be interpreted as instructions by the agent.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata