sparc-methodology

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the 'claude-flow' package on the NPM registry and its source code repository on GitHub. These references target established services for the distribution and maintenance of the framework's tooling.
  • [COMMAND_EXECUTION]: The methodology instructions include the use of npx to execute the 'claude-flow' CLI. This is a standard execution method for Node.js-based development utilities and is necessary for the skill's orchestration functionality.
  • [PROMPT_INJECTION]: The 'researcher' and 'reviewer' modes ingest data from the web and external repositories, creating an indirect prompt injection surface.
  • Ingestion points: External content is introduced via WebSearch and WebFetch in the researcher mode, and through the analysis of GitHub repositories and pull requests in the analyzer and reviewer modes.
  • Boundary markers: The skill's instructions do not define specific delimiters or security warnings to prevent the agent from executing instructions embedded within this external data.
  • Capability inventory: The agent is granted capabilities to execute shell commands via npx and perform file system modifications through the coder mode.
  • Sanitization: There is no description of sanitization or validation processes for the external data before it is incorporated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 06:40 AM
Security Audit — agent-trust-hub — sparc-methodology