arch-discover

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands such as find, grep, and ls to audit the project's layout and search for specific code patterns (e.g., Controllers, Services, Repositories). These commands are used to identify technologies and existing code conventions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local data from the repository being inspected, creating a risk that malicious content in the code could mislead the agent's analysis or instructions.
  • Ingestion points: The skill reads project-specific files including dependency manifests (e.g., package.json, Cargo.toml), source code files, and existing docs/adr/ documentation.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore instructions embedded in the analyzed repository content.
  • Capability inventory: The skill has the capability to read local files, execute search commands, and trigger the arch-manage skill to create new documentation artifacts.
  • Sanitization: No sanitization or filtering logic is defined for the content extracted from the project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 08:06 PM
Security Audit — agent-trust-hub — arch-discover