task-coordinator

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists exclusively of instructional Markdown and YAML configuration metadata. It contains no executable scripts, binaries, or automated shell commands. It includes an attribution link to a public repository for methodology references.
  • [NO_CODE]: There are no source code files (such as Python, JavaScript, or shell scripts) included in the skill, which reduces the potential for logic-based vulnerabilities or malicious background execution.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to ingest and process user-provided task descriptions and system requirements.
  • Ingestion points: Task scopes, goals, and discovery question answers defined in SKILL.md.
  • Boundary markers: The instructions do not provide specific delimiters or ignore-embedded-instruction warnings for processing user-supplied task data.
  • Capability inventory: The skill is instructional and does not possess built-in execution tools, though it facilitates the orchestration of other agent workflows.
  • Sanitization: No mechanisms for validating or filtering external task inputs are described in the methodology.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 11:25 AM
Security Audit — agent-trust-hub — task-coordinator