report-template-generator

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill lacks security constraints while requesting tools with significant system impact.
  • Ingestion points: The skill activates on and processes user-supplied requests and data concerning "report template generator" patterns (SKILL.md).
  • Boundary markers: Absent. There are no instructions to the agent to distinguish between its own logic and data-embedded instructions.
  • Capability inventory: The skill is granted Bash, Write, and Edit tools (SKILL.md YAML), allowing for arbitrary code execution and file system modification.
  • Sanitization: No sanitization, validation, or escaping protocols are mentioned for the data analytics inputs or generated outputs.
  • Command Execution (MEDIUM): The explicit request for Bash and Write capabilities for a template generation task follows the principle of most privilege rather than least privilege, increasing the potential impact of any successful injection.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 12:00 AM