ln-63-release-publisher

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill defines a highly structured workflow that minimizes autonomous risk by requiring human approval before publication.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository which creates a potential attack surface.
  • Ingestion points: Git commit history, commit bodies, and repository manifests (e.g., package.json, version.txt) mentioned in SKILL.md.
  • Boundary markers: The requirement for explicit user approval of the final proposal serves as the primary boundary.
  • Capability inventory: Shell command execution (Git, GitHub CLI) and file system access for manifest updates and release notes defined in SKILL.md.
  • Sanitization: The skill mandates using a file for release notes to prevent shell injection during publication.
  • [COMMAND_EXECUTION]: The skill uses Git and GitHub CLI commands to perform its release tasks. This is standard functionality for the described purpose and includes safeguards such as using a host credential store and avoiding echoing secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 05:03 AM
Security Audit — agent-trust-hub — ln-63-release-publisher