sagemaker-endpoint-deployer
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to activate on user-provided triggers and generate code or configurations using powerful system tools. It lacks explicit boundary markers or instructions to sanitize external data, creating a potential for the agent to follow malicious instructions embedded within user requests.
- Ingestion points: Processes user requests triggered by phrases like "sagemaker endpoint deployer", "sagemaker deployer", or "deploy sagemaker endpoint er" (found in SKILL.md).
- Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore instructions embedded in the user's domain-specific deployment requests.
- Capability inventory: The skill is configured with access to
Read,Write,Edit,Grep, and unrestrictedBashcommands in its execution environment. - Sanitization: No sanitization, validation, or filtering mechanisms are specified in the instructions for handling user-supplied deployment parameters or context.
Audit Metadata