Skills
skills/ably/agent-skills/debugging-with-ably-cli/Gen Agent Trust Hub

debugging-with-ably-cli

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill enables the agent to run various ably CLI commands to observe and simulate realtime traffic for troubleshooting purposes.
  • [EXTERNAL_DOWNLOADS]: Mentions the installation of the official @ably/cli package via npm, which is a verified resource provided by the authoring vendor.
  • [PROMPT_INJECTION]: The skill involves processing live data from external messaging channels via commands like ably subscribe and ably logs, which presents an inherent surface for indirect prompt injection.
  • Ingestion points: ably subscribe, ably logs, and ably presence subscribe (referenced in SKILL.md).
  • Boundary markers: None identified; external data is not delimited from agent instructions.
  • Capability inventory: The agent has the capability to publish messages, manage application settings, and issue authentication tokens through the CLI.
  • Sanitization: No sanitization or validation logic is specified for data received from subscription channels.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 02:11 AM