slack
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses
curlto interact with Slack's official Web API endpoints for messaging and management tasks. - [DATA_EXFILTRATION]: Accesses the
$SLACK_TOKENenvironment variable to authenticate requests and retrieves workspace information, including message history and user profiles, which is necessary for its intended functionality. - [PROMPT_INJECTION]: The skill processes untrusted data from Slack messages and files, creating a potential surface for indirect prompt injection.
- Ingestion points: Retrieves data through
conversations.history,conversations.replies,search.messages,search.files, andfiles.infoas documented inSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when processing retrieved content.
- Capability inventory: The skill has broad capabilities including sending messages (
chat.postMessage), managing users (users.profile.set), and deleting files (files.delete) across its documented functions. - Sanitization: No explicit sanitization or filtering of data retrieved from the Slack API is specified in the skill instructions.
Audit Metadata