remofirst-sdk-patterns

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates patterns for fetching and handling data from an external HR API (RemoFirst), which introduces an attack surface for indirect prompt injection where malicious instructions could be embedded in the API response.\n
  • Ingestion points: External data is ingested through the RemoFirstClient.get("/employees", ...) method call documented in SKILL.md.\n
  • Boundary markers: Absent. The skill provides no delimiters or instructions to the agent to treat API response content as untrusted or to ignore embedded instructions.\n
  • Capability inventory: The skill allows the use of powerful tools including Write, Edit, and Bash (with npm and curl access), which could be misused if the agent follows instructions provided in external data.\n
  • Sanitization: Absent. There is no evidence of data validation, sanitization, or schema enforcement on the external content before it is processed in the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 07:17 PM
Security Audit — agent-trust-hub — remofirst-sdk-patterns