task-decomposer

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection (Category 8) as it processes untrusted user input within the 'problem-description' parameter.
  • Ingestion points: The 'problem-description' argument as defined in 'SKILL.md'.
  • Boundary markers: There are no defined delimiters or instructions to ignore embedded commands within the user-provided content.
  • Capability inventory: The skill possesses file-system access capabilities through the 'Read', 'Grep', and 'Glob' tools listed in its configuration.
  • Sanitization: No sanitization, escaping, or validation logic is applied to the incoming task descriptions before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 10:15 AM
Security Audit — agent-trust-hub — task-decomposer