bookstrap-export-project
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes common shell commands such as cp, zip, tar, and mktemp to perform file system operations and create project archives.
- [COMMAND_EXECUTION]: It executes local scripts within the skill's environment, specifically ./scripts/backup-db.sh and python ./scripts/generate-export-manifest.py, to facilitate the export process.
- [DATA_EXFILTRATION]: The skill aggregates project-wide data, including potentially sensitive configuration files (bookstrap.config.json) and database backups, into a single portable archive.
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing untrusted manuscript files and source documents during the export task.
- Ingestion points: Files within the manuscript/ directory and ingested source documents.
- Boundary markers: No boundary markers or delimiters are employed to isolate data from potential instructions during the archiving process.
- Capability inventory: File system manipulation utilities (cp, zip, tar) and execution of local shell and Python scripts.
- Sanitization: No validation or sanitization of the content being exported is performed.
Audit Metadata