harper-best-practices

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for deploying applications via the Harper CLI (harper deploy_component). While this is a standard operational procedure, it involves the use of shell commands and the management of sensitive cluster credentials.- [PROMPT_INJECTION]: Documentation includes examples of handling user-provided search prompts to generate embeddings and query the database (e.g., in rules/vector-indexing.md). This creates an attack surface for indirect prompt injection where untrusted input can influence the agent's behavior or data retrieval process.- [SAFE]: The skill explicitly incorporates security-conscious guidelines, such as recommending role-based access control checks for privileged actions and providing clear warnings regarding the risks of destructive database operations in rules/programmatic-table-requests.md.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 08:17 PM
Security Audit — agent-trust-hub — harper-best-practices