lint
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes shell commands including
atmos,git, and a locally built binary./custom-gcl. This is part of the intended linting and fixing functionality. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of linter output which is then passed to a subagent for processing and automated fixing. This represents an attack surface where malicious code comments or patterns could influence the agent's file modifications. 1. Ingestion points: Raw output from
custom-gclinSKILL.md. 2. Boundary markers: Not explicitly defined in the provided file. 3. Capability inventory: File modification (vialint-fixagent),git add,git push, and shell command execution. 4. Sanitization: Relies on the subagent's logic; no explicit sanitization described in the skill instructions.
Audit Metadata