aiagent-env-manager

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates credential management by executing a local script tools/credential_manager.py using the uv Python tool. This script is used to securely store keys and verify their status without printing sensitive values.
  • [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by taking user-supplied keys as arguments for CLI commands. However, the instructions include safety guidelines to prevent secret leakage and emphasize local-only storage.
  • Ingestion points: User-provided key names used in the store <KEY> command (SKILL.md).
  • Boundary markers: None present in the prompt instructions to delimit the user input within the command.
  • Capability inventory: Execution of shell commands via uv run to interact with a local Python script (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the <KEY> argument is described in the prompt text.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 05:58 AM
Security Audit — agent-trust-hub — aiagent-env-manager