sparc-methodology

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input via the task_description parameter, which is then passed to various specialized agents within the orchestration framework.
  • Ingestion points: The task_description field in mcp__claude-flow__sparc_mode and related orchestration calls in SKILL.md serves as a primary entry point for untrusted data.
  • Boundary markers: The instructions do not define or implement delimiters (e.g., XML tags or specific markers) to separate user data from system instructions, nor do they provide explicit warnings to the agent to ignore instructions embedded within the data.
  • Capability inventory: The framework provides agents with significant capabilities, including autonomous code generation (coder), file system operations (batch-executor), network access (researcher), and shell command execution via the CLI.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the input data before it is interpolated into the agent's context.
  • [COMMAND_EXECUTION]: The skill provides numerous examples and workflows involving the execution of shell commands through the npx claude-flow CLI, including usage of the @alpha release channel.
  • [EXTERNAL_DOWNLOADS]: The methodology relies on fetching the claude-flow package and its dependencies from the NPM registry at runtime via npx commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 03:08 PM