sc-pr-check
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill programmatically identifies and executes a wide variety of local development tools including linters (ruff, eslint, clippy), formatters (prettier, black), type checkers (mypy, tsc), and test runners (pytest, cargo test) based on detected configuration files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted output from external tools (such as test failures and security scan results) to suggest remediation actions, which presents a surface for instructions embedded in logs or code to influence agent behavior.
- Ingestion points: Linter results, test failure logs, and source code files (SKILL.md).
- Boundary markers: The behavior flow does not specify the use of delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill uses shell execution and file modification tools to perform remediation.
- Sanitization: No explicit sanitization or filtering of external tool output is described.
Audit Metadata