skills/tw93/mole/release-flow/Gen Agent Trust Hub

release-flow

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard command-line tools such as git, gh (GitHub CLI), grep, go, and make to manage the project release lifecycle and perform pre-flight verification.\n- [EXTERNAL_DOWNLOADS]: Fetches update scripts and release binaries from the author's official GitHub repository at raw.githubusercontent.com/tw93/mole.\n- [REMOTE_CODE_EXECUTION]: The mo update functionality is designed to download and execute an install.sh script from the project's repository. This is the intended update path for the CLI tool and operates via the author's trusted infrastructure.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests external project data which could theoretically be used for prompt injection if the source were malicious. \n
  • Ingestion points: git log (commit messages) and gh release view (release body). \n
  • Boundary markers: No specific delimiters or safety instructions are defined for processing this data. \n
  • Capability inventory: git push, gh release edit, make build, and execution of the post-reactions.sh script. \n
  • Sanitization: No explicit sanitization of ingested logs or release text is performed. \n This surface is inherent to the release management use case and represents a low-risk profile for this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 11:55 AM