dead-code
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project source code as input for its static analysis functions.
- Ingestion points: The
tldrtool scans the project directory (.) and source folders (src/) to identify dead code. - Boundary markers: The instructions lack specific delimiters or "ignore instructions" directives to prevent the agent from potentially following malicious instructions embedded within the analyzed code comments or strings.
- Capability inventory: The skill utilizes the
Bashtool to execute CLI commands for code analysis and architecture mapping. - Sanitization: No sanitization or validation of the codebase content is mentioned prior to ingestion and analysis.
Audit Metadata