recommending-test-layers
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources including Jira, Confluence, and GitHub PRs. It mitigates risks by instructing the agent to treat this content as untrusted data rather than instructions, specifically mentioning CWE-1427 precautions. Evidence: SKILL.md.
- [COMMAND_EXECUTION]: The skill uses the
ghcommand-line tool via a bash interface to retrieve PR details. It restricts these operations to the bitwarden organization and mandates user confirmation. Evidence: SKILL.md. - [EXTERNAL_DOWNLOADS]: The skill retrieves information from well-known services, including GitHub repositories and Confluence pages. Evidence: SKILL.md.
Audit Metadata