skills/gendosu/agkan-skills/release/Gen Agent Trust Hub

release

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard command-line tools, including git and jq, to manage the repository state and versioning information. These operations are essential to its primary function of software release management.
  • [DATA_EXFILTRATION]: The skill performs git push operations to the remote repository (origin). While this involves network transmission, it is the intended and primary purpose of the skill to synchronize release tags and version updates with the central repository.
  • [SAFE_PRACTICE]: The instructions explicitly forbid the use of broad staging commands like git add . or git add -A. Instead, they mandate staging only specific files (.claude-plugin/plugin.json and CHANGELOG.md), which minimizes the risk of accidentally committing sensitive data or unauthorized scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data by reading the CHANGELOG.md and plugin.json files. While these files could theoretically contain malicious instructions, the skill's narrow scope and manual update instructions for the agent provide a structured environment that reduces the risk of unintended behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 06:43 AM