skills/ssiumha/dots/lint-audit/Gen Agent Trust Hub

lint-audit

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill runs several development tools like tsc, eslint, ruff, and mypy using shell commands. This is intended behavior for a linting audit tool but involves executing potentially untrusted binaries if the project environment is compromised.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8).
  • Ingestion points: Processes commit messages via git log and source code content via find and cat for SLOC calculation.
  • Boundary markers: No explicit delimiters or instructions are used to separate ingested content from the agent's logic.
  • Capability inventory: Extensive local command execution capabilities (npx, git, bash, find).
  • Sanitization: No sanitization is performed on the data read from the repository before it is processed by the agent.
  • [DATA_EXFILTRATION] (SAFE): While the skill accesses project files and history, there are no network operations or indicators of data being sent to external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 03:27 PM