Skills
Navigate
skills/slackapi/slack-cli/record-demo/Gen Agent Trust Hub

record-demo

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates and executes .tape DSL files using the vhs CLI tool to automate terminal sessions and record output.
  • [EXTERNAL_DOWNLOADS]: Instructions are provided for the user to install the vhs utility via Homebrew (brew install vhs) if the dependency is not found.
  • [PROMPT_INJECTION]: The skill incorporates user-supplied text from $ARGUMENTS into the generated tape file without sanitization, creating a surface for indirect prompt injection. \n
  • Ingestion points: User input provided via the $ARGUMENTS variable in SKILL.md. \n
  • Boundary markers: None; the input is directly interpolated into the tape file template. \n
  • Capability inventory: The skill executes the vhs command (which runs a shell) and the open command. \n
  • Sanitization: None; the agent is not instructed to validate or escape the provided command description.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 03:21 AM
Security Audit — agent-trust-hub — record-demo