changelog

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_CONTEXT_INJECTION]: The skill executes shell commands at load time to populate context with recent git history (git log) and resolve configuration using a project-local script (yaml-helper.sh). These operations are consistent with the skill's purpose for project maintenance.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git logs and external project files, creating a potential surface for indirect injection. \n
  • Ingestion points: Data is read from git log output, production/sprints/, and design/gdd/ as defined in Phase 2.\n
  • Boundary markers: The skill includes a 'Provenance check' section with explicit instructions for the agent to classify and validate the relevance of commit subjects before proceeding.\n
  • Capability inventory: The skill utilizes Bash, Write, Read, Glob, and Grep tools to gather data and save the final changelog.\n
  • Sanitization: Instructions in Phase 5 and the 'Guidelines' section direct the agent to filter out technical jargon, code references, and internal names for the player-facing version.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 06:51 PM
Security Audit — agent-trust-hub — changelog