slackbot
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
npxpackage runner to execute the@useclawlink/clitool for authentication (login), connection, and action execution within Slack. - [EXTERNAL_DOWNLOADS]: Fetches the
@useclawlink/clipackage from the official NPM registry to perform Slack operations. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill reads data and metadata from Slack workspaces via the
actionsandruncommands of the CLI. - Boundary markers: There are no explicit instructions or delimiters defined to isolate external data from the agent's core instructions.
- Capability inventory: The agent can search, describe, and execute arbitrary Slackbot actions via shell commands.
- Sanitization: The instructions do not describe any sanitization or validation of the data retrieved from Slack before it is returned to the agent's context.
Audit Metadata