slackbot
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses npx to execute the @useclawlink/cli tool to perform actions such as logging in, connecting services, and running Slackbot commands.
- [EXTERNAL_DOWNLOADS]: The skill downloads the @useclawlink/cli package from the NPM registry during execution.
- [CREDENTIALS_UNSAFE]: The skill documentation specifies that authentication credentials are stored locally at ~/.clawlink/credentials.json.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it retrieves and processes data from Slackbot.
- Ingestion points: Data from Slackbot is ingested into the agent context via npx @useclawlink/cli run slackbot in SKILL.md.
- Boundary markers: No explicit boundary markers or instructions to isolate external data are present in the skill instructions.
- Capability inventory: The skill enables the agent to execute shell commands and perform Slack workspace actions through the ClawLink CLI.
- Sanitization: No data sanitization or input validation logic is defined for the content retrieved from Slackbot.
Audit Metadata