obsidian-project-bootstrap
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script to detect and bootstrap project memory. It uses environment variables and the current working directory as arguments.
- Evidence: Shell commands in
SKILL.mdcallpython3on a script located at${CLAUDE_PLUGIN_ROOT}/skills/obsidian-project-memory/scripts/project_kb.py. - [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection, as it is instructed to read informative documentation and code from the current repository to synthesize durable notes.
- Ingestion points: Files within the repository root (
$PWD) being processed. - Boundary markers: None specified to differentiate between repo content and agent instructions.
- Capability inventory: Ability to execute shell commands via a Python script and perform file system write operations to the Obsidian vault.
- Sanitization: No sanitization or filtering of the ingested content is mentioned.
Audit Metadata