skills/mono0926/skills/release-pub/Gen Agent Trust Hub

release-pub

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs Git operations (commit, tag, push) and uses the GitHub CLI (gh) to create releases and monitor workflow runs. These actions are fundamental to its stated purpose of automating the package release process.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to pub.dev (the official Dart package registry) and refers to documentation on dart.dev. It also references an official GitHub Actions workflow from the dart-lang organization. These interactions target well-known and trusted services associated with the skill's primary function.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of Git commit messages to generate release notes and CHANGELOG.md entries.
  • Ingestion points: Commit logs fetched via git log as described in SKILL.md.
  • Boundary markers: The instructions specify that the agent should categorize commits and generate notes in English, but no explicit "ignore embedded instructions" delimiters are used for the log data itself.
  • Capability inventory: Includes file system writes, Git commands, GitHub CLI commands, and execution of a local Dart helper script (release_helper).
  • Sanitization: The skill relies on the agent to analyze, categorize, and summarize the commits into a structured markdown format before writing them to the changelog.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 12:58 AM
Security Audit — agent-trust-hub — release-pub