agent-workloads

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill interpolates user-supplied intent strings into shell commands, creating a potential command injection surface. 1. Ingestion points: User intent parameter in SKILL.md. 2. Boundary markers: Double quotes are used but are insufficient against shell metacharacters. 3. Capability inventory: Use of joelclaw CLI for task planning and execution. 4. Sanitization: Absent; no validation or escaping instructions.
  • [COMMAND_EXECUTION]: The skill guides the agent in executing local CLI commands (joelclaw) to manage repository workflows and task dispatching.
  • [EXTERNAL_DOWNLOADS]: The skill mentions npx skills add to install external extensions, which involves downloading code from remote registries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 12:38 PM
Security Audit — agent-trust-hub — agent-workloads