changelog-forge

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script scripts/forge.py. This is the primary function of the skill to process repository history and format it for release notes.- [PROMPT_INJECTION]: This skill processes commit messages from git history, which represents an indirect prompt injection surface where untrusted data could influence the agent's output.
  • Ingestion points: Git commit messages read by scripts/forge.py.
  • Boundary markers: Not defined in the skill instructions.
  • Capability inventory: Bash tool access and file-write capabilities for CHANGELOG.md.
  • Sanitization: Not explicitly mentioned in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 08:47 PM
Security Audit — agent-trust-hub — changelog-forge