weekly-review
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute local Python scripts (
scripts/open_loop_scanner.py,scripts/weekly_review_gate.py, andscripts/commitment_auditor.py) to automate the review process. These scripts are implemented using only the Python standard library and do not perform network requests or modify system configuration. - [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by reading data from potentially untrusted files in the user's workspace.
- Ingestion points:
scripts/open_loop_scanner.pyreads markdown files and source code from user-specified directories to extract unchecked checkboxes and TODO/FIXME markers. - Boundary markers: No explicit delimiters or system instructions are used to distinguish extracted text snippets from the agent's primary instructions.
- Capability inventory: The agent can read files, execute the provided Python scripts, and interact with the user to manage the review checklist.
- Sanitization: Extracted text snippets are presented to the agent without escaping or sanitization, allowing for potential instructions embedded in scanned content to be interpreted by the AI.
Audit Metadata