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
Bashtool to execute standard filesystem and search commands to discover files and verify symbol usage. - Evidence:
SKILL.mdcontains templates forfind(Step 2) andgrep(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.mdStep 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, andReadtools acrossSKILL.mdand referenced project files. - Sanitization: No explicit sanitization or filtering of the source code content is performed before data extraction.
Audit Metadata