write-root-readme
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests repository content to generate a summary for the README file. This represents an attack surface where untrusted data from the codebase could influence the agent's output. The skill includes instructions for the agent to spot-check information against repository files and run a formatting tool for validation, which serves as a basic integrity check.\n- [EXTERNAL_DOWNLOADS]: The example README template includes numerous references to external assets, such as project images from Socialify and status badges from Shields.io, Codecov, and GitHub. These references target well-known and reputable services commonly used for open-source documentation.\n- [COMMAND_EXECUTION]: The skill requires the execution of
rumdl fmt .to validate the formatting of the generated README.rumdlis a markdown linter and formatter used to maintain code quality.
Audit Metadata