sam-cloudformation

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, potentially untrusted data including GitHub Actions logs, CircleCI migration notes, and AWS CloudFormation stack events to diagnose failures.
  • Ingestion points: CI deployment logs, AWS CloudFormation stack event histories, and IAM trust policy configurations (SKILL.md, references/oidc-assumerole-triage.md).
  • Boundary markers: The instructions do not specify the use of delimiters or clear separation between the ingested external logs and the agent's internal instructions.
  • Capability inventory: The skill suggests executing significant infrastructure commands, including sam deploy and aws cloudformation continue-update-rollback (SKILL.md, references/deploy-checklist.md).
  • Sanitization: No explicit validation or sanitization routines are defined for processing the content of captured logs or policy snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 05:29 PM