release-skills

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands using git and the GitHub CLI (gh) to analyze repository history, identify contributors, and automate the commit, tagging, and pushing of release artifacts.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because it ingests untrusted data from external sources to generate user-facing changelogs. * Ingestion points: Untrusted data enters via git commit messages and metadata retrieved from the GitHub API using gh pr view. * Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the ingested commit logs. * Capability inventory: The skill possesses the authority to write to the local file system and execute network-altering commands like git push. * Sanitization: There is no evidence of escaping or validation of the text retrieved from git history before it is interpolated into project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 03:45 PM