slack-web-api
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill retrieves content from external Slack channels, threads, and search results, which are untrusted data sources.
- Ingestion points: The
channelHistory,threadReplies, andsearchMessagesfunctions inscripts/slack_web_api.tsfetch raw message data from the Slack API. - Boundary markers: The tool outputs raw JSON content to stdout without including delimiters or warnings to the agent about ignoring potential instructions embedded in the data.
- Capability inventory: The script facilitates network communication with Slack's official API and allows reading local files for message content.
- Sanitization: The script does not perform any validation or sanitization on the text retrieved from Slack messages before returning it to the agent.
Audit Metadata