cohere

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the NPM registry. This tool is provided by the skill vendor to manage service connections and API requests.
  • [COMMAND_EXECUTION]: The instructions utilize the membrane CLI for various operations, including authentication (membrane login), connection management (membrane connection ensure), and executing Cohere actions (membrane action run).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data generated by Cohere models (e.g., text generation, summaries, chatbot responses), which could contain instructions that influence the agent's behavior.
  • Ingestion points: Cohere API responses such as generated text and chat responses described in SKILL.md.
  • Boundary markers: None identified; the skill does not explicitly instruct the agent to use delimiters or ignore instructions embedded within the API responses.
  • Capability inventory: The skill can execute actions (membrane action run) and perform network operations via a proxy (membrane request), as detailed in SKILL.md.
  • Sanitization: The instructions do not specify any validation or sanitization for the data retrieved from the external API.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 04:10 PM