bmad-party-mode

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external data to generate personas and conversation context, which could be exploited to override agent behavior.
  • Ingestion points: The skill ingests 'source data' such as profiles and survey exports in references/create-party.md and reads session history from .memlog.md files in references/party-memory.md.
  • Boundary markers: The instructions do not specify explicit structural delimiters or instructions for the model to ignore embedded commands when processing raw input data.
  • Capability inventory: The skill has access to subprocess.run (via scripts/resolve_party.py), triggers file writes (via bmad-customize), and uses web search tools.
  • Sanitization: No explicit sanitization, filtering, or validation logic is defined for the ingested data.
  • [COMMAND_EXECUTION]: The skill executes local Python scripts as part of its normal activation and state management flows.
  • Evidence: scripts/resolve_party.py uses subprocess.run() to execute roster.py, resolve_config.py, and resolve_customization.py.
  • Evidence: references/party-memory.md invokes memlog.py to append session data to memory logs.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing dependencies from the vendor's repository if they are missing from the environment.
  • Evidence: SKILL.md instructs the user to run npx skills add bmad-code-org/BMAD-METHOD --skill bmad to install the base framework.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 10:20 PM