skills/commet-labs/skills/commet-cli/Gen Agent Trust Hub

commet-cli

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill determines its operational capabilities by reading local manifest files and parsing the output of the installed CLI tool. This ingestion of external data creates a surface for indirect prompt injection if the local environment or vendor tools are compromised.
  • Ingestion points: Output of commet --output agent, commet doctor, and the node_modules/@commet/node/docs/manifest.json file.
  • Boundary markers: The instructions explicitly require the agent to state exact targets and wait for user authorization before performing any local file writes or remote resource mutations.
  • Capability inventory: The skill can perform repository writes, link organizations, push configuration, and create remote resources via the CLI.
  • Sanitization: The skill mandates that the agent never print secret values or credentials and warns the user before authentication flows.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 06:38 PM