aws-review
Warn
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill attempts to locate and read AWS credential files, specifically searching for '**/.aws/credentials' in the discovery step. Accessing such files is a significant security risk as they typically contain long-term authentication secrets and sensitive configuration data.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests various infrastructure-as-code files, which introduces a risk of indirect prompt injection where malicious instructions could be embedded in the analyzed data. Evidence Chain: 1. Ingestion points: The skill uses Glob to find .tf, .yaml, and .json files (SKILL.md). 2. Boundary markers: The skill includes a 'Prompt Injection Safety Notice' in SKILL.md. 3. Capability inventory: The skill is authorized to use Read, Grep, and Glob tools. 4. Sanitization: No explicit technical sanitization of analyzed file content is documented.
Audit Metadata