aws-lambda-go-deployment
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing external data (CloudWatch logs) which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: CloudWatch Logs are accessed to troubleshoot runtime-startup and init failures, as noted in SKILL.md and references/packaging-checklist.md.
- Boundary markers: The skill lacks instructions to wrap log content in delimiters or include warnings to ignore embedded instructions within the data.
- Capability inventory: The skill performs file system operations and executes shell commands such as go build and sam build (SKILL.md).
- Sanitization: No sanitization or validation steps are defined for the logs being processed.
Audit Metadata