e2e-testing
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides a URL to fetch a replacement SKILL.md file from the author's repository on GitHub.
- [COMMAND_EXECUTION]: Instructs the agent to suggest a command (pnpm dlx skills add) to install the updated skill. This instruction includes an explicit requirement to obtain user consent before proceeding.
- [INDIRECT_PROMPT_INJECTION]: The skill points to an external resource (the e2etest skill) and instructs the agent to follow its rules.
- Ingestion points: SKILL.md fetched from the author's repository
- Boundary markers: None present
- Capability inventory: The agent follows instructions from the downloaded skill
- Sanitization: None present
Audit Metadata