user-changelog

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands including git log, git rev-parse, grep, and sed to extract commit history and parse the existing changelog file. It also invokes bun run check via a related skill to validate changes before committing.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) as it processes untrusted Git commit subjects and bodies to generate summaries.
  • Ingestion points: Commit data is ingested via git log in SKILL.md (Step 2).
  • Boundary markers: No explicit delimiters or instructions are used to ignore embedded commands within the commit messages.
  • Capability inventory: The agent has the capability to write to the local file system (docs/user-changelog.md) and execute bun scripts/git commands.
  • Sanitization: The skill does not sanitize the input commit messages before processing them into German bullets.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 03:37 AM
Security Audit — agent-trust-hub — user-changelog