skills/brycewang-stanford/awesome-agent-skills-for-empirical-research/obsidian-project-lifecycle/Gen Agent Trust Hub
obsidian-project-lifecycle
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to execute a Python script (
project_kb.py) for file management tasks like archiving and permanent deletion. The script is located in a sibling directory (../obsidian-project-memory/scripts/) belonging to the same project ecosystem. - [PROMPT_INJECTION]: The skill defines an attack surface where user-provided inputs, such as file paths and names, are passed directly as command-line arguments to a shell command.
- Ingestion points: Filenames and destination paths provided by the user for the
--noteand--destarguments inSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands within the input data.
- Capability inventory: The skill has the capability to move, rename, and permanently delete files on the local file system via the
project_kb.pyscript. - Sanitization: There are no instructions within the skill to sanitize or validate the user-provided paths before execution.
Audit Metadata