bmad-os-changelog-social

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Utilizes local shell commands including git tag and git log to extract versioning data and contributor history from the repository.- [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by ingesting and processing content from files that can be modified by external contributors.
  • Ingestion points: Reads from CHANGELOG.md, .claude-plugin/marketplace.json, and git commit history via git log.
  • Boundary markers: No explicit delimiters or instructions to ignore instructions within the ingested data are defined.
  • Capability inventory: Executes shell commands (git) and performs file system write operations to the _bmad-output/social/ directory.
  • Sanitization: Does not perform validation or sanitization of the extracted text before incorporating it into social media templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 06:17 PM