sparc-methodology
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
claude-flowpackage, which is hosted on NPM and GitHub. These references are to official vendor resources on well-known services. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, creating a potential surface for indirect prompt injection.
- Ingestion points: The
researchermode performs web searches and fetches external content, while thereviewerandanalyzermodes process codebases and dependency information from the project environment. - Boundary markers: The skill does not explicitly define delimiters or specific 'ignore instructions' warnings for external content processed by its modes.
- Capability inventory: The skill has significant capabilities including code implementation (
coder), test execution (tdd), network access (researcher), and version control interaction (github_pr_manage). - Sanitization: There are no explicit sanitization or filtering instructions for content retrieved from external sources before it is processed by the agent.
Audit Metadata