ln-624-code-quality-auditor
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to run static analysis utilities such asradon,gocyclo, andeslint-plugin-complexity. It also executes an internal script,references/scripts/evaluation-runtime/cli.mjs, which manages the evaluation lifecycle and state transitions.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it analyzes external, untrusted source code.\n - Ingestion points: The skill reads source code from the target project using the
ReadandGreptools as part of its auditing workflow.\n - Boundary markers: While the skill uses a 'Two-Layer Detection' methodology to verify findings through context analysis, it lacks explicit prompt delimiters to isolate the ingested code snippets.\n
- Capability inventory: The skill possesses significant capabilities, including filesystem access and shell command execution via the
Bashtool.\n - Sanitization: There are no instructions to sanitize or escape the source code content before it is processed by the agent.
Audit Metadata