skills/raptoravis/tunan/release-notes/Gen Agent Trust Hub

release-notes

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches release notes and pull request metadata from GitHub's official API and the raptoravis/tunan repository. These references to well-known services and the author's own repository are handled safely.
  • [COMMAND_EXECUTION]: Executes the gh CLI and a local Python helper script. Subprocess calls are constructed using argument lists rather than raw shell strings, which effectively prevents command injection vulnerabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from GitHub release bodies. It incorporates explicit defensive instructions for the agent to treat this data as documentation only and to disregard any embedded directives or instructions.
  • [DYNAMIC_EXECUTION]: The helper script allows the path to the gh binary to be overridden via an environment variable (CE_RELEASE_NOTES_GH_BIN). This dynamic path resolution is a standard configuration pattern for testing and environment flexibility.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 09:10 PM