slackcli
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
slackclitool via the Homebrew tapshaharia-lab/tap. - [COMMAND_EXECUTION]: The skill instructs the agent to execute various
slackclisubcommands to interact with Slack workspaces, including reading conversations and sending messages. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external data (Slack messages, DMs, and search results) that could contain malicious instructions.
- Ingestion points: Slack conversations and messages fetched via
slackcli conversations readandslackcli search messagesinSKILL.md. - Boundary markers: Absent; the instructions do not specify delimiters or warn the agent to ignore instructions embedded within the Slack content.
- Capability inventory: The agent can perform write actions such as sending messages (
slackcli messages send) or adding reactions (slackcli messages react) based on the processed content. - Sanitization: Absent, though the skill mandates a human-in-the-loop check by requiring the agent to confirm intent before performing write actions.
Audit Metadata