api-spec

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a Python script to validate the generated documentation index.
  • Evidence: python3 <technical-spec dir>/scripts/check_index.py --specs-dir docs/api-specs in SKILL.md.
  • Context: This is a utility command designed for project maintenance to ensure that the _index.md file correctly reflects the contents of the docs/api-specs/ directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project documentation and code definitions, which provides a surface for indirect prompt injection.
  • Ingestion points: Technical specifications (docs/technical-specs/), business requirements (docs/business/), and existing API definition files (e.g., OpenAPI, gRPC proto) as described in Phase 1 of SKILL.md.
  • Boundary markers: Absent; the instructions do not define delimiters to separate source material from agent instructions.
  • Capability inventory: The skill is capable of writing documentation files to the local file system and executing a local validation script.
  • Sanitization: Absent; the skill does not explicitly perform sanitization on the content retrieved from the documentation files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 02:49 AM