dead-code-audit

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because it is designed to read and analyze untrustworthy data from repositories, including source code, comments, and manifest files.
  • Ingestion points: Manifest files (e.g., package.json, pyproject.toml, Cargo.toml, go.mod) and source code files as described in SKILL.md and references/tool-selection.md.
  • Boundary markers: No explicit delimiters or instructions are provided to separate audited data from agent instructions or to ignore embedded commands within the files.
  • Capability inventory: The agent is authorized to read files and execute multiple repository-native and auditing tools (e.g., npm, cargo, go, ruff, eslint, ripgrep, staticcheck, vulture, and cargo udeps).
  • Sanitization: There is no evidence of sanitization or validation of the audited content before processing.
  • [COMMAND_EXECUTION]: The skill instructs the agent to run project-native commands and scripts (e.g., existing lint scripts and test commands defined in package.json). This presents a risk of executing arbitrary code if the audited repository contains malicious script definitions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 03:37 PM