commit
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various build and maintenance commands, including
pnpm install,cargo test,pytest, and directory cleanup usingfindandrm. These commands are standard for the intended development workflow in this repository. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it analyzes untrusted repository data to perform its tasks.
- Ingestion points: Data enters the agent context through
git status,git diff --cached, and by reading project files likeCLAUDE.mdand source code. - Boundary markers: None identified. There are no instructions for the agent to use delimiters or specific ignore rules to distinguish between the skill's instructions and the content of the files it is analyzing.
- Capability inventory: The agent has the ability to execute shell commands, perform file system operations, and run various test suites.
- Sanitization: The skill does not implement any validation, escaping, or filtering of the content ingested from the repository files.
Audit Metadata