skills/mukul975/anthropic-cybersecurity-skills/detecting-aws-iam-privilege-escalation/Gen Agent Trust Hub
detecting-aws-iam-privilege-escalation
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes IAM policies retrieved from AWS APIs or local files, creating a potential surface for indirect prompt injection attacks where malicious data in the policy documents could influence the agent's behavior.
- Ingestion points: Data is ingested via the AWS
GetAccountAuthorizationDetailsAPI or user-provided JSON files in thescripts/agent.pyscript. - Boundary markers: No explicit delimiters or instructions are used to distinguish untrusted policy data from analysis logic.
- Capability inventory: The skill has the ability to read from the local file system, write JSON reports to the file system, and interact with AWS APIs using the
boto3library. - Sanitization: Policy content is parsed as JSON but lacks specific sanitization or filtering to detect or remove potential injection patterns before processing.
Audit Metadata