specstory-organize
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script (
scripts/organize.py) that handles file organization. This is a legitimate and expected operation for its stated purpose. \n- [DATA_EXFILTRATION]: No network operations or attempts to access sensitive system files (e.g., credentials, SSH keys) were found. The skill's scope is limited to the.specstory/historyfolder within the current working directory. \n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of local filenames. \n - Ingestion points:
scripts/organize.pyreads filenames usingos.listdir(). \n - Boundary markers: Not applicable to filename parsing logic. \n
- Capability inventory: Includes directory creation (
os.mkdir) and file movement (shutil.move) within the project structure. \n - Sanitization: The script utilizes a strict regular expression (
^(\\d{4})-(\\d{2})-\\d{2}_) to extract year and month data, which prevents path traversal and ensures that only appropriately named files are processed.
Audit Metadata