websocket
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external source code, which constitutes an indirect prompt injection surface. This behavior is expected for a security auditing tool.
- Ingestion points: The workflow identifies and reads files matching patterns like
**/ws/**,**/websocket/**, and**/handlers/**for analysis (SKILL.md, Step 1). - Boundary markers: The skill does not explicitly define unique delimiters or instructions to ignore potential commands embedded in the source code during manual analysis.
- Capability inventory: The skill uses
semgrepfor automated detection and instructs the agent to perform manual analysis to identify WebSocket security flaws (SKILL.md, Step 3 & 4). - Sanitization: No explicit sanitization or filtering of the source code content is performed before it is analyzed by the agent.
- [COMMAND_EXECUTION]: The skill executes the
semgrepscanner to identify vulnerabilities in the code. This is a standard operation for a security tool and utilizes a well-known industry utility.
Audit Metadata