slack
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external Slack messages and search results, which constitutes a potential attack surface for indirect prompt injection.
- Ingestion points: Slack conversation history, thread replies, and search results are fetched via the
conversations.history,conversations.replies, andassistant.search.contextAPI endpoints inSKILL.md. - Boundary markers: The skill does not define specific boundary markers or delimiters for the ingested message content before it is processed by the agent.
- Capability inventory: The skill utilizes the
Bashtool to perform shell operations and network requests viacurl. - Sanitization: API responses are processed using
jqto extract specific JSON fields, which prevents shell command injection during the data extraction phase. However, the raw text content of messages is passed to the agent context. - [DATA_EXFILTRATION]: The skill manages sensitive Slack authentication tokens (
$SLACK_TOKENand$SLACK_USER_TOKEN). These tokens are used correctly as Bearer tokens in headers for requests directed exclusively tohttps://slack.com/api/and the author's official console athttps://studio.acedata.cloud/.
Audit Metadata