code-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill executes shell commands automatically when loaded to populate context about the developer environment.
- Evidence:
!git diff --name-only HEAD~3 2>/dev/null || echo "no git history"`` inSKILL.md. - Evidence:
!swift --version 2>&1 | head -1 || echo "swift not found"`` inSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes external source code, which serves as a potential vector for instructions embedded within the data being processed.
- Ingestion points: Reads local Swift source code files using the
XcodeGlob,XcodeGrep, andXcodeReadtools as instructed inSKILL.md. - Boundary markers: Absent; there are no explicit delimiters or instructions provided to the agent to disregard commands embedded within the analyzed code.
- Capability inventory: The skill is primarily focused on read-only analysis, architecture mapping, and generating a review report; no file-writing or network-exfiltration capabilities are observed.
- Sanitization: Absent; the protocol does not specify any sanitization or escaping of the ingested source code content before it enters the agent's context.
Audit Metadata