aws-review
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill intentionally locates and reads sensitive files such as
~/.aws/credentialsand.envfiles to perform its security assessment. While these are high-value targets, the skill's restricted toolset (Read, Grep, Glob) and lack of network access prevent unauthorized data transfer. These actions are consistent with the skill's stated purpose of auditing AWS environments. - [PROMPT_INJECTION]: As the skill parses third-party code and configuration files, it is subject to indirect prompt injection. The developer included explicit instructions in the 'Prompt Injection Safety Notice' to treat ingested text as non-executable data, reducing the risk of the agent following malicious instructions embedded in the analyzed infrastructure-as-code.
Audit Metadata