certificate-lifecycle-manager

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill identifies a data ingestion surface for processing certificate-related requests which could contain malicious instructions.
  • Ingestion points: User requests and mentioned certificate lifecycle tasks.
  • Boundary markers: Absent; there are no instructions to the agent to treat external data as untrusted or delimited.
  • Capability inventory: The skill has access to Bash, Write, and Edit tools via the allowed-tools manifest.
  • Sanitization: Absent; no validation or escaping logic is described in the manifest.
  • [Command Execution] (LOW): The skill explicitly allows the Bash tool. While functional for managing certificates (e.g., using OpenSSL), this powerful capability increases the risk if the agent is influenced by malicious input.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:18 PM