software-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data including pull request diffs, merge requests, and AI-generated code (ingestion points in SKILL.md). It lacks explicit boundary markers or sanitization logic to prevent the agent from being influenced by malicious instructions embedded within the code under review. The skill's capability inventory includes the potential invocation of external CLI tools such as linters and scanners, as well as the execution of a local feedback script located at agents-skills-feedback-loop/scripts/append_learning.py.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and configuration files from various external repositories and services in data/sources.json. These include trusted organizations such as Anthropic, Google, and Microsoft, alongside established technology providers like Alibaba, Snyk, and Trail of Bits. These references are used to fetch established code review standards and are consistent with the skill's purpose.
Audit Metadata