remofirst-install-auth

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process data from the RemoFirst API, which serves as a potential vector for indirect prompt injection if the external data contains instructions intended to override agent behavior.
  • Ingestion points: Data is retrieved from the RemoFirst API endpoint (/company) in SKILL.md and processed via the RemoFirstClient class.
  • Boundary markers: The instructions do not define clear boundary markers or delimiters to separate untrusted external data from the agent's internal instruction set.
  • Capability inventory: The skill utilizes the Python requests library for network operations and has access to environment variables for credential storage. The platform manifest also enables file system access tools (Read, Write, Edit).
  • Sanitization: There is no evidence of data sanitization, schema validation, or content filtering for the data returned by the API before it is utilized by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 07:17 PM
Security Audit — agent-trust-hub — remofirst-install-auth