code-simplifier
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code and configuration files, creating a potential surface for instructions embedded in external data. This risk is inherent to the skill's purpose as a code refactoring tool.
- Ingestion points: Target files identified for simplification,
docs/project-config.json, and reference documentation likecode-review-rules.mdandproject-structure-reference.md. - Boundary markers: The skill does not implement specific delimiters or "ignore" markers for the content it reads.
- Capability inventory: The skill can read/write files, execute local project scripts (e.g.,
.claude/scripts/code_graph), and spawn subagents for specialized tasks. - Sanitization: No sanitization of ingested code or documentation is performed.
- [SAFE]: The skill's instructions use imperative language ("BLOCKING", "MANDATORY") to enforce a specific workflow, which is a benign pattern for complex AI agent skills. No attempts to bypass safety filters, execute remote code, or exfiltrate data were identified.
Audit Metadata