maintain-packaging

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of standard procedural instructions for software maintenance, focusing on dependency management, metadata consistency, and licensing audits.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local scripts (scripts/licensing/license_diff.py) and development tools (uv, pre-commit) via uv run. These commands are scoped to the project environment and represent routine development tasks for the stated purpose of maintaining the codebase.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for auditing and updating external dependency manifests and lockfiles (Cargo.toml, pyproject.toml, uv.lock, package.json).
  • Ingestion points: Project-specific manifest and lockfiles in SKILL.md Audit Areas.
  • Boundary markers: None explicitly defined for the file parsing process.
  • Capability inventory: Execution of local scripts and pre-commit hooks using uv run and build operations via maturin and just.
  • Sanitization: The skill mitigates risks by requiring manual review from "dependency approvers" for all license and dependency changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 12:39 AM
Security Audit — agent-trust-hub — maintain-packaging