dead-code-auditor

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute standard filesystem and search commands to discover files and verify symbol usage.
  • Evidence: SKILL.md contains templates for find (Step 2) and grep (Step 4) used to automate the identification of code symbols and their references across the project directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code as input during its audit workflow, creating a potential surface for indirect prompt injection if the code contains adversarial instructions.
  • Ingestion points: The skill reads all project files in SKILL.md Step 3 ("Read every file in the target").
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts are defined for the file-reading process.
  • Capability inventory: The skill utilizes Bash, Grep, and Read tools across SKILL.md and referenced project files.
  • Sanitization: No explicit sanitization or filtering of the source code content is performed before data extraction.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 01:36 AM
Security Audit — agent-trust-hub — dead-code-auditor