herdr-pre-release-audit

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill workflow involves executing shell commands such as git describe, git log, and just release-docs-check. It allows for user-provided input ($1) to be used as a git reference in these commands, creating a potential vector for command misuse if inputs are not properly validated.
  • [PROMPT_INJECTION]: The skill processes untrusted information from git commit logs and pull request metadata, creating a surface for indirect injection attacks.
  • Ingestion points: The audit process reads git commit history, commit bodies, and pull request titles/bodies (File: references/pre-release-audit.md).
  • Boundary markers: No explicit delimiters or instructions to disregard embedded commands in the source data are provided.
  • Capability inventory: The skill can execute local commands (git, just) and write to documentation files in the repository.
  • Sanitization: The processed commit and PR data are not sanitized or filtered before being analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 05:30 PM
Security Audit — agent-trust-hub — herdr-pre-release-audit