architecture-map

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses structural code evidence such as manifests, entrypoints, and routes to build architecture diagrams, which is a safer approach than relying on natural language descriptions.
  • [COMMAND_EXECUTION]: The skill requires access to the project's version control system to obtain the 'source commit' for documentation versioning, implying the execution of shell commands like git.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from various project files, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: Project manifests, build files, configs, routes, entrypoints, and deployment descriptors as defined in SKILL.md.
  • Boundary markers: None present; the skill lacks delimiters or instructions to ignore embedded prompts in the analyzed code.
  • Capability inventory: The agent can read local files and write Markdown documentation to the filesystem.
  • Sanitization: No sanitization or validation of the ingested content is specified before it is used to generate diagrams and descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 05:26 PM
Security Audit — agent-trust-hub — architecture-map