propagate-design-change

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes and analyzes content from Game Design Documents (GDDs) and Architectural Decision Records (ADRs) to identify stale decisions.\n
  • Ingestion points: Phase 2 and Phase 4 read full document contents from design/gdd/ and docs/architecture/.\n
  • Boundary markers: There are no explicit instructions to the agent to treat document content as untrusted or to use delimiters to prevent instruction injection.\n
  • Capability inventory: The skill has file-writing capabilities, can execute shell commands, and can spawn other agents via the Task tool.\n
  • Sanitization: No sanitization or validation of the ingested text is performed before it is used to influence the workflow.\n- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill executes a git command that incorporates a user-supplied file path.\n
  • Evidence: In Phase 3, the command git show HEAD:design/gdd/[filename].md is executed using the Bash tool.\n
  • Discussion: While the skill verifies the file's existence on disk before execution, constructing shell commands from user-provided input is a potential injection vector.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:19 PM
Security Audit — agent-trust-hub — propagate-design-change