fusion-issue-author-task

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or security violations were detected. The skill consists of instructional markdown and structured task templates.
  • [DATA_EXFILTRATION]: The skill implements a security-positive constraint by explicitly prohibiting direct mutations (e.g., API calls to create issues). It restricts its output to local markdown drafts, ensuring that all external actions are handled by a verified orchestrator.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes a standard data ingestion surface where user-provided task objectives are formatted into templates. This is a primary function and carries minimal risk as the output remains local.
  • Ingestion points: Task objective, scope, and dependency constraints defined as required inputs in SKILL.md.
  • Boundary markers: Absent; the skill uses standard markdown headers in templates without specific delimiters for untrusted content.
  • Capability inventory: The skill utilizes the agent's file-system capability to write drafts to the .tmp/ directory.
  • Sanitization: No explicit sanitization or validation of input content is described before template interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 01:17 AM