assemble-changelog

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands including git, rg, and find. It also invokes project-specific scripts such as pixi run uvpy scripts/generate_changelog.py and various CI check scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted data from external PR contributors.
  • Ingestion points: Reads and parses content from multiple files in docs/content/changelog/upcoming/*.md (referenced in SKILL.md).
  • Boundary markers: None identified; instructions do not include delimiters or warnings to ignore instructions embedded within the changelog entries.
  • Capability inventory: The skill has allowed-tools for Bash, Read, Edit, and Write, and it executes a Python-based generator script.
  • Sanitization: None identified; the skill directly incorporates prose and structure from the incoming markdown files into the final release changeset.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:44 AM
Security Audit — agent-trust-hub — assemble-changelog