simplify
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the
simplifyingskill from the author's GitHub repository (github.com/alexandru/skills) using thenpxcommand. - [COMMAND_EXECUTION]: The skill executes shell commands to manage dependencies via
npxand runs the project's internal test suite during the verification phase. - [DYNAMIC_EXECUTION]: The skill automatically executes project-specific tests and checks to verify behavior-preserving changes, which involves running local code.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted source code and diffs which could contain adversarial instructions targeting the subagent.
- Ingestion points: Source files and diffs provided via the scope defined in
SKILL.md. - Boundary markers: No explicit markers are used to separate code from instructions for the subagent in
SKILL.mdorreferences/reviewer.md. - Capability inventory: The skill can modify the file system and execute shell commands (tests).
- Sanitization: No sanitization or filtering is applied to the ingested code.
Audit Metadata