simplify
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection (Category 8). It ingests untrusted source code data (Ingestion points: SKILL.md using
gitandReadtools), lacks explicit boundary markers to separate data from instructions, possesses powerful capabilities (Capability inventory:Editfor file modification andBashfor command execution), and does not apply sanitization to the ingested code content. - [COMMAND_EXECUTION]: The skill uses the
Bashtool to run developer commands includinggit diff,npm run typecheck,npm test, and search tools likeast-grep(sg). - [EXTERNAL_DOWNLOADS]: The skill uses
npxto execute packages likejscpdandtsc, which may result in downloading dependencies from the npm registry during execution.
Audit Metadata