skills/hubvue/skills/release-skills/Gen Agent Trust Hub

release-skills

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git commands including git log, git diff, git commit, and git tag to manage the repository state and analyze changes. These operations are standard for a release automation tool.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from git commit logs to generate changelogs and determine version bumps. 1. Ingestion points: Commit history data retrieved via git log and git diff in Step 1. 2. Boundary markers: None. There are no delimiters specified to isolate log data from the prompt logic. 3. Capability inventory: The skill can modify local markdown files and the marketplace.json file, and it can execute git commit and tagging commands. 4. Sanitization: No sanitization or validation of commit message content is performed before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 07:24 AM