aws-iam

Warn

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: MEDIUMDATA_EXFILTRATIONREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill directs the agent to search for AWS environment information within potentially sensitive project files.
  • Instructions in references/aws-iam-policy-generation.md (Task 1b) mandate checking .env, terraform.tfvars, cdk.json, cdk.context.json, and samconfig.toml for account IDs and regions. Accessing these files, which are standard locations for storing secrets, poses a significant data exposure risk.
  • [REMOTE_CODE_EXECUTION]: The skill uses uvx to download and execute an external tool for analyzing source code at runtime.
  • Executes uvx iam-policy-autopilot@latest generate-policies to derive IAM policies from application code. The tool is maintained by the awslabs organization on GitHub, an official repository for Amazon Web Services.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to interact with the environment and development tools.
  • Runs aws sts get-caller-identity to retrieve current account details.
  • Executes the iam-policy-autopilot CLI to generate permissions.
  • [EXTERNAL_DOWNLOADS]: The skill fetches official AWS service definitions from a remote endpoint.
  • Queries https://servicereference.us-east-1.amazonaws.com to map API operations to the correct IAM actions.
  • [PROMPT_INJECTION]: The skill ingests untrusted application source code to automate policy generation, creating a surface for indirect prompt injection.
  • Ingestion points: Analyzes source code files in Python, Go, TypeScript, and Java provided by the user in references/aws-iam-policy-generation.md.
  • Boundary markers: No specific delimiters or safety instructions are defined for the source code content being processed.
  • Capability inventory: The skill has access to shell execution (aws, uvx) and network operations (curl).
  • Sanitization: Risk is mitigated by the use of the iam-policy-autopilot tool, which performs deterministic static analysis rather than relying on LLM reasoning to interpret the code, reducing the likelihood of malicious instructions influencing the output.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 24, 2026, 03:53 PM
Security Audit — agent-trust-hub — aws-iam