workflow

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection vulnerability surface through its handling of user-defined tasks. \n
  • Ingestion points: User-provided strings (e.g., in the usage examples in SKILL.md) are passed directly as parameters to workflow commands. \n
  • Boundary markers: Absent. No explicit delimiters or guardrail instructions are provided in SKILL.md to separate user-provided data from system instructions. \n
  • Capability inventory: As listed in SKILL.md, the skill is authorized to use Bash, Write, Edit, and Skill (the ability to execute other agent skills). \n
  • Sanitization: Absent. There is no evidence of validation or sanitization of user input strings before they are processed by the orchestration logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 03:11 AM