creating-changelog-entries

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard CLI tools such as towncrier, uv, and poetry to manage changelog fragments. These tools are used as intended for project maintenance tasks.
  • [PROMPT_INJECTION]: The skill defines a command structure that interpolates user-controlled data (issue IDs and change descriptions) into shell commands. This is a common surface for indirect prompt injection in CLI-based skills, which relies on the agent platform's execution layer to handle shell escaping.
  • Ingestion points: Issue identifiers, change types, and user-provided descriptions in SKILL.md.
  • Boundary markers: None identified in the provided command templates.
  • Capability inventory: Shell command execution via uv or poetry in SKILL.md.
  • Sanitization: Not explicitly defined in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 09:10 PM
Security Audit — agent-trust-hub — creating-changelog-entries