insomnia-collection-generator

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a workflow to scan codebase routes from a source directory, which constitutes an ingestion point for untrusted data processed to generate the final export file.\n
  • Ingestion points: The scanRoutes function (referenced in scripts/insomnia-gen.ts) ingests data from the user-specified source directory path.\n
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are specified in the output generation logic.\n
  • Capability inventory: The skill uses fs.writeFileSync to save the generated JSON collection to the local file system.\n
  • Sanitization: The output is structured as valid JSON, providing implicit formatting, but the skill lacks explicit logic to sanitize input data from the codebase to prevent potential injection into the final export resource.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:31 AM
Security Audit — agent-trust-hub — insomnia-collection-generator