skills/acedatacloud/skills/slack/Gen Agent Trust Hub

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, and assistant.search.context API endpoints in SKILL.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 Bash tool to perform shell operations and network requests via curl.
  • Sanitization: API responses are processed using jq to 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_TOKEN and $SLACK_USER_TOKEN). These tokens are used correctly as Bearer tokens in headers for requests directed exclusively to https://slack.com/api/ and the author's official console at https://studio.acedata.cloud/.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 07:32 PM