scrum-master
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODEEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and analyze external data like project backlogs, definition of done, and team maturity assessments. This ingestion of untrusted data creates a potential surface for indirect prompt injection, particularly as the agent is permitted to use the Bash tool.\n
- Ingestion points: Workflow Phase 1 (SKILL.md) specifies reviewing existing artifacts and the project backlog.\n
- Boundary markers: The instructions do not provide delimiters or specific warnings to distinguish between instructions and external data content.\n
- Capability inventory: The skill is configured with access to Bash, Read, Grep, and Glob tools.\n
- Sanitization: There are no explicit instructions for the agent to sanitize, escape, or validate content read from external artifacts.\n- [NO_CODE]: The skill consists entirely of Markdown instructions and reference guides. No Python scripts, Node.js modules, or shell scripts are included in the skill package.\n- [EXTERNAL_DOWNLOADS]: The skill documentation refers to an external repository (krzysztofsurdy/code-virtuoso) for additional architectural knowledge. This is a reference to a resource by the same author and serves as a recommended integration.
Audit Metadata