slack-openapi-skill
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a curated OpenAPI schema from the vendor's official GitHub repository (holon-run/uxc). This is a standard operation for defining API interactions within the uxc tool's environment and is documented neutrally as it originates from the verified developer source.
- [COMMAND_EXECUTION]: Utilizes the uxc CLI tool to perform setup and manage authentication bindings for Slack API interactions. These operations are within the expected scope of the tool's functionality.
- [PROMPT_INJECTION]: The skill processes message data from Slack (ingestion points: conversations.history and conversations.replies as defined in SKILL.md and references/slack-web.openapi.json). This creates a surface for indirect prompt injection. However, the risk is mitigated by explicit instructions to require user confirmation before executing write operations (capability inventory: chat.postMessage and reactions.add). No specific boundary markers or sanitization logic are provided in the skill instructions.
- [SAFE]: Interacts with the Slack API using authentication tokens. The skill documentation follows security best practices by guiding users to store sensitive bot and user tokens in environment variables rather than hardcoding them in the command line or configuration files.
Audit Metadata