obsidian-arrow-composition
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses find and grep shell commands to traverse the src/ directory and analyze component imports. These are standard development utilities used for codebase analysis.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes the content of arbitrary code files in the project.
- Ingestion points: Processes all .ts files within the src/components/ and src/views/ directories.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to prevent it from following commands that might be hidden within code comments or string literals.
- Capability inventory: The agent can execute shell commands (find, grep) and write new documentation files to the docs/plans/ directory.
- Sanitization: No sanitization or filtering of the source code content is performed before the agent analyzes and summarizes it.
Audit Metadata