skills/plastic-labs/honcho/pre-pr/Gen Agent Trust Hub

pre-pr

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes command-line tools such as git for diffing, gh (GitHub CLI) for issue metadata retrieval, and uv for running linters and tests. These actions are standard for the intended workflow of preparing a pull request and are limited to the local environment and the official GitHub repository plastic-labs/honcho.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on data retrieved from external GitHub issues.
  • Ingestion points: Untrusted data is ingested from GitHub issues using the gh issue view command in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions (e.g., "ignore embedded instructions") are used to segregate external issue content from the agent's internal instructions when determining PR readiness.
  • Capability inventory: The skill possesses command execution capabilities (git, gh, uv) and file-write capabilities (filling the pull request template).
  • Sanitization: The skill does not perform sanitization on the issue metadata fields (such as title or labels) before they are incorporated into the agent's decision-making context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 10:47 AM