book-author-orchestrator
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the discovery of academic references through well-known scholarly services including Crossref, arXiv, PubMed/NCBI, Europe PMC, and Semantic Scholar. It also includes an update mechanism that checks the vendor's official GitHub repository (
github.com/lensetek/Book-Author-Agent-Skills) for skill updates, requiring explicit user confirmation before any download. - [COMMAND_EXECUTION]: The orchestrator invokes several helper Python scripts (
validate_references.py,fetch_evidence_snippet.py,parse_rps.py,build_cpmk_matrix.py,graphify_harness.py) located within the skill's local directory structure to perform data parsing and validation tasks. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data such as research papers, thesis notes, and course plans (RPS).
- Ingestion points: Research papers, thesis/dissertation notes, and RPS files provided by the user.
- Boundary markers: The instructions mandate a 'security/privacy scan' and the use of a 'book-security-privacy-checker' before processing content.
- Capability inventory: The skill executes local Python scripts, writes project checklists, and routes tasks to specialized agents for writing and export.
- Sanitization: Implements a mandatory privacy checker at intake and finalization to flag and redact PII, credentials, and sensitive respondent data.
- [SAFE]: The skill provides explicit instructions to protect user privacy and academic integrity. It includes features to detect and flag credentials or private data in inputs and focuses on verifiable academic standards.
Audit Metadata