obsidian-prod-checklist
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands and Node.js execution to validate project configuration files and run build scripts. These actions are standard for development and CI/CD workflows and align with the skill's primary purpose.
- [DATA_EXFILTRATION]: Includes a script that searches the user's local source code for strings matching common secret patterns (API keys, tokens, passwords). This is a defensive feature intended to prevent the user from accidentally publishing sensitive credentials.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes external files (manifests and source code) from the local environment. Malicious content within these analyzed files could potentially attempt to influence agent behavior.
- Ingestion points:
manifest.json,package.json, and thesrc/directory in the local workspace. - Boundary markers: None identified.
- Capability inventory: Shell command execution (
Bash), file system access, and Node.js script execution. - Sanitization: The skill does not perform sanitization on the content read from files before it is processed or displayed.
Audit Metadata