building-websocket-server

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a restricted Bash tool Bash(api:websocket-*) to automate server scaffolding, boilerplate generation, and the implementation of endpoint handlers as described in SKILL.md and references/implementation.md.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface through its handling of external configuration files.
  • Ingestion points: Untrusted data in the form of existing API specifications is read from the {baseDir}/api-specs/ directory.
  • Boundary markers: The instructions do not define any delimiters or explicit boundary markers to isolate external content from the agent's instruction context.
  • Capability inventory: The skill has access to Bash(api:websocket-*), Write, and Edit tools, which could be leveraged if malicious instructions were present in the ingested data.
  • Sanitization: No sanitization or validation logic is specified for the data retrieved from the API specifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 12:28 AM