sagemaker-endpoint-deployer

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill possesses a potential attack surface for indirect prompt injection due to the interaction between untrusted user input and high-privilege tool access.
  • Ingestion points: Untrusted data enters the agent context through user requests triggered by phrases like 'sagemaker endpoint deployer'.
  • Boundary markers: The skill definition lacks explicit delimiters or instructions to prevent the agent from obeying commands embedded within user data.
  • Capability inventory: The skill is configured to use 'Bash', 'Write', 'Edit', and 'Read' tools (SKILL.md).
  • Sanitization: No evidence of input escaping, validation, or content filtering is provided in the skill documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 03:04 PM